blueswarm image.png
Swarm robotics involves scores of individual mobile robots that mimic the collective behavior demonstrated by animals. Certain robots, like the Bluebot pictured here, perform some of the same behaviors as a school of fish, such as aggregation, dispersion, and searching.
Courtesy of Radhika Nagpal, Harvard University

Schooling robots to behave like fish

Radhika Nagpal has created robots that can build towers without anyone in charge. Now she’s turned her focus to fulfillment center robots.

When Radhika Nagpal was starting graduate school in 1994, she and her future husband went snorkeling in the Caribbean. Nagpal, who grew up in a landlocked region of India, had never swum in the ocean before. It blew her away.

“The reef was super healthy and colorful, like being in a National Geographic television show,” she recalled. “As soon as I put my face in the water, this whole swarm of fish came towards me and then swerved to the right.”

Meet the Blueswarm
Blueswarm comprises seven identical miniature Bluebots that combine autonomous 3D multi-fin locomotion with 3D camera-based visual perception.

The fish fascinated her. As she watched, large schools of fish would suddenly stop or switch direction as if they were guided by a single mind. A series of questions occurred to her. How did they communicate with one another? What rules — think of them as algorithms — produced such complex group behaviors? What environmental prompts triggered their actions? And most importantly, what made collectives so much smarter and more successful than their individual members?

Radhika Nagpal is a professor of computer science at Harvard University’s Wyss Institute for Biologically Inspired Engineering and an Amazon Scholar
Radhika Nagpal is a professor of computer science at Harvard University’s Wyss Institute for Biologically Inspired Engineering and an Amazon Scholar.

Since then, Nagpal, a professor of computer science at Harvard University’s Wyss Institute for Biologically Inspired Engineering and an Amazon Scholar, has gone on to build swarming robots. Swarm robotics involves scores of individual mobile robots that mimic the collective behavior demonstrated by animals, e.g. how flocks of birds or schools of fish move together to achieve some end. The robots act as if they, too, were guided by a single mind, or, more precisely, a single computer. Yet they are not.

Instead, they follow a relatively simple set of behavioral rules. Without any external orders or directions, Nagpal’s swarms organize themselves to carry out surprisingly complex tasks, like spontaneously synchronizing their behavior, creating patterns, and even building a tower.

More recently, her lab developed swimming robots that performed some of the same behaviors as a school of fish, such as aggregation, dispersion, and searching. All without a leader.

Nagpal’s work demonstrates both how far we have come in creating self-organizing robot swarms that can perform tasks — and how far we still must go to emulate the complex tapestries woven by nature. It is a gap that Nagpal hopes to close by uncovering the secrets of swarm intelligence to make swarm robots far more useful.

Amorphous computing

The Caribbean fish sparked Nagpal’s imagination because she was already interested in distributed computing, where multiple computers collaborate to solve problems or transfer information without any single computer running the show. At MIT, where she had begun her PhD program, she was drawn to an offshoot of the field called amorphous computing. It investigates how limited, unreliable individuals — from cells to ants to fish — organize themselves to perform often complex tasks consistently without any hierarchies.

Amorphous computing was “hardware agnostic.” This meant that it sought rules that guided this behavior in both living organisms and computer systems. It asked, for example, how identical cells in an embryo form all the organs of an animal, how ants find the most direct route to food, or how fish coordinate their movements. By studying nature, these computer scientists hoped to build computer networks that operated on the same principles.

I got excited about how nature makes these complicated, distributed, mobile networks. Those multi-robot systems became a new direction of my research
Radhika Nagpal

After completing her doctoral work on self-folding materials inspired by how cells form tissues, Nagpal began teaching at Harvard. While there, she was visited by her friend James McLurkin, a pioneer in swarm robotics at MIT and iRobot.

“James is the one that got me into robot swarms by introducing me to all the things that ant and termite colonies do,” Nagpal said. “I got excited about how nature makes these complicated, distributed, mobile networks. James was developing that used similar principles to move around and work together. Those multi-robot systems became a new direction of my research.”

She was particularly taken by Namibian termites, which build large-scale nest mounds with multiple chambers and complex ventilation systems, often as high as 8 feet tall.

“As far as we know, there isn’t a blueprint or an a priori distribution between who’s doing the building and who is not. We know the queen does not set the agenda,” she explained. “These colonies start with hundreds of termites and expand their structure as they grow.”

The question fascinated her. “I have no idea how that works,” she said. “I mean, how do you create systems that are so adaptive?”

Finding the rules

Researchers have spent decades answering that question. One way, they found, is to act locally. Take, for example, a flock of geese at a pond. If one or two birds on the outside of the flock see a predator, they grow agitated and fly off, alerting the next nearest birds. The message percolates through flock. Once a certain number of birds have “voted” to fly off, the rest follow without any hesitation. They are not following a leader, only reacting only to the birds next to them.

How dynamic circle formation works

The same type of local behaviors could be used to make driverless vehicles safer. An autonomous vehicle, Nagpal explains, does not have to reason about all the other cars on the road, only the ones around it. By focusing on nearby vehicles, these distributed systems use less processing power without losing the ability to react to changes very quickly.

Such systems are highly scalable. “Instead of having to reason about everybody, your car only has to reason about its five neighbors,” Nagpal said. “I can make the system very large, but each individual’s reasoning space remains constant. That’s a traditional notion of scalable —the amount of processing per vehicle stays constant, but we’re allowed to increase the size of the system.”

Another key to swarm behavior involves embodied intelligence, the idea that brains interact with the world through bodies that can see, hear, touch, smell, and taste. This is a type of intelligence, too, Nagpal argues.

It’s almost like each individual fish acts like a distributed sensor. Instead of me doing all the work, somebody on the left can say, ‘Hey, I saw something.’ When the group divides the labor so that some of us look out for predators while the rest of us eat, it costs less in terms of energy and resources.
Radhika Nagpal

“When you think of an ant, there is not a concentrated set of neurons there,” she said, referring to the ant’s 20-microgram brain. “Instead, there is a huge amount of awareness in the body itself. I may wonder how an ant solves a problem, but I have to realize that somehow having a physical body full of sensors makes that easier. We do not really understand how to think about that still.”

Local actions, scalable behavior, and embodied intelligence are among the factors that make swarms successful. In fact, researchers have shown that the larger a school of fish, the more successful it is at evading predators, finding food, and not getting lost.

“It’s almost like each individual fish acts like a distributed sensor,” Nagpal said. “Instead of me doing all the work, somebody on the left can say, ‘Hey, I saw something.’ When the group divides the labor so that some of us look out for predators while the rest of us eat, it costs less in terms of energy and resources than trying to eat and look out for predators all by yourself.

“What’s really interesting about large insect colonies and fish schools is that they do really complicated things in a decentralized way, whereas people have a tendency to build hierarchies as soon as we have to work together,” she continued. “There is a cost to that, and if we try to do that with that with robots, we replicate the whole management structure and cost of a hierarchy.”

So Nagpal set out to build robots swarms that worked without top-down organization.

Animal behavior

A typical process in Nagpal’s group starts by identifying an interesting natural behavior and trying to discover the rules that generate those actions. Sometimes, they are surprisingly simple.

Take, for example, some behaviors exhibited by Nagpal’s colony of 1,000 interactive robots, each the size of quarter and each communicating with its nearest neighbors wirelessly. The robots will self-assemble into a simple line with a repeating color pattern based on only two rules: a motion rule that allows them to move around any stationary robots, and a pattern rule that tells them to take on the color of their two nearest neighbors.

Other combinations of simple rules spontaneously synchronize the blinking of robot lights, guide migrations, and get the robots to form the letter “K.”

Most impressively, Nagpal and her lab used a behavior found in termites, called stigmergy, to prompt self-organized robot swarms to build a tower. Stigmergy involves leaving a mark on the environment that triggers a specific behavior by another member of the group.

Stigmergy plays a role in how termites build their huge nests. One termite may sense that a spot would make a good place to build, so it puts down its equivalent of a mud brick. When a second termite comes along, the brick triggers it to place its brick there. As the number of bricks increase, the trigger grows stronger and other termites begin building pillars nearby. When they grow high enough, something triggers the termites to begin connecting them with roofs.

“The building environment has become a physical memory of what should happen next,” Nagpal said.

Nagpal used that type of structural memory to prompt her robotic swarm to build a ziggurat tower. The instructions included a motion rule about how to move through the tower and a pattern rule about where to place the blocks. She then built some small, block-carrying robots that built a smaller but no less impressive structure.

Her lab developed a compiler that could generate algorithms that would enable the robots to build specific types of structures — perhaps towers with minarets — by interacting with stigmergic physical memories. One day, algorithm-driven robots could move sandbags to shore up a levee in a hurricane or buttress a collapsed building. They could even monitor coral reefs, underwater infrastructure, and pipelines — if they could swim.

Schooling robofish

From the start, Nagpal wanted to build her own school of robotic fish, but the hardware was simply too clunky to make them practical. That changed with the advent of smartphones, with their low-cost, low-power processors, sensors, and batteries.

In 2018, she got her chance when she received an Amazon Machine Learning Research Award. This allowed her to build Blueswarm, a group of robotic fish that performed tasks like those she observed in the Caribbean years ago.

Each Bluebot is just four inches long, but it packs a small Raspberry Pi computer, two fish-eye cameras, and three blue LED lights. It also has a tail (caudal) fin for thrust, a dorsal fin to move up or down, and side fins (pectoral fins) to turn, stop, or swim backward.

Bluebots do not use Wi-Fi, GPS, or external cameras to communicate their positions without error. Instead, she wants to explore what behaviors are possible relying only on cameras and local perception of one’s mates.

How multi-behavior search works

Researchers, she explained, find it difficult to rely only upon local perception. It has been difficult to tackle fundamental questions, like how does a robot visually detect other members of the swarm, how they parse information, and what happens when one member moves in front of another. Limiting Bluebot sensing to local perception forces Nagpal and her team to think more deeply about what robots really need to know about their neighbors, especially when data is limited and imprecise. 

Bluebots can mimic several fish school behaviors by tracking LED lights on the neighboring fishbots around them. Using 3D cameras and simple algorithms, they estimate distance between lights on neighboring fish. (The closer they appear, the further the fish.)

Nagpal’s seven Bluebots form a circle (called milling) by turning right if there is a robot in front of them. If there is no robot, they turn left. After a few moments, the school will be swimming in a circle, a formation fish use to trap prey.

They can also search for a target flashing red light. First, the school disperses within the tank. When a Bluebot finds the red LED, it begins to flash its lights. This signals the nearest Bluebots to aggregate, followed by the rest. If a single robot had to conduct a similar search by itself, it would take significantly longer.

These behaviors are impressive for robots, but represent a small subset of fish school behaviors. They also take place in a static fish tank populated by only one school of robot fish. To go further, Nagpal wants to improve their sensors and perhaps use machine learning to discover new rules that could be combined to produce the aquatic equivalent of a tower.

In the end, though, Nagpal does not want to build a better fish. Instead, she wants to apply the lessons she has learned to real-world robots. She is doing just that during a sabbatical working at Amazon, which operates the largest fleet of robots — more than 200,000 units — in the world.

Practical uses

Nagpal had little previous experience working in industry, but she jumped at the chance to work with Amazon.

“There are few others with hundreds of robots moving around safely in a facility space,” she said. “And the opportunity to work on algorithms in a deployed system was very exciting."

There are few others [like Amazon] with hundreds of robots moving around safely in a facility space. And the opportunity to work on algorithms in a deployed system was very exciting.
Radhika Nagpal

“The other factor is that Amazon’s robots do a mix of centralized and decentralized decision-making," she continued. "The robots plan their own paths, but they also use the cloud to know more. That lets us ask: Is it better to know everything about all your neighbors all the time? Or is it better to only know about the neighbors that are closer to you?”

Her current focus is on sortation centers, where robots help route packages to shipping stations sorted by ZIP codes. Not surprisingly, robots setting out from multiple points to dozens of different locations require a degree of coordination. Amazon’s robots are already aware of other robots. If they see one, they will choose an alternate route. But what path should they take, Nagpal asks. She wants to make sure those robots are making the most effective possible choices.

Cities already manage this. They limit access to some roads, change speed limits, and add one-way streets. Computer networks do it as well, rerouting traffic when packet delivery slows down.

Some of those concepts, such as one-way travel lanes, also work in sortation centers. They could act as stigmergic signals to guide robot behavior. She also believes there might be a way to create simple swarm behaviors that enable robots to react to advanced data about incoming packages.

Once her sabbatical is over, Nagpal plans to return to the lab. She wants to keep working on her Bluebots, improving their vision, and turning them loose in environments that look more like the coral reef she went snorkeling in 25 years ago.

She is also dreaming of swarms of bigger robots for use in construction or trash collection.

“Maybe we could do what Amazon is doing, but do it outside,” she said. “We could have swarms of robots that actually do some sort of practical task. At Amazon, that task is delivery. But given Boston’s snowstorms, I think shoveling the sidewalks would be nice.”

Research areas

Related content

US, WA, Seattle
Amazon's eCommerce Foundation (eCF) organization provides the core technologies that drive and power Amazon's Stores, Digital, and Other (SDO) businesses. Millions of customer page views and orders per day are enabled by the systems eCF builds from the ground up. CloudTune, within eCF, empowers growth and business agility needs by automatically and efficiently managing AWS capacity and business processes needed to safely meet Amazon's customer demand. CloudTune serves its primary customers, internal software teams, through forecast-driven automation of cost controllership, capacity management, and scaling. We predict expected load, and drive procurement and allocation of AWS capacity for new product launches and high-velocity events like Prime Day and Cyber Monday. CloudTune is looking for a Data Scientist to join our forecasting and optimization team. The team develops sophisticated algorithms that combine machine learning-based demand forecasting with mathematical optimization to solve large-scale capacity planning problems under uncertainty. We work with massive datasets — spanning thousands of availability zone and instance family combinations across global regions — to determine optimal resource allocation strategies that balance infrastructure holding costs against service availability requirements. These models directly inform multi-million dollar capacity investment decisions and drive automated procurement, retention, and release policies across Amazon's compute infrastructure. As a Data Scientist in CloudTune, you will work with other scientists, software engineers, data engineers, and product managers on a variety of important research problems in the areas of stochastic optimization, time series modeling, and operations research. You will work on statistical problems with a high level of ambiguity. You will analyze and process large amounts of data, develop new algorithms and improve existing approaches based on statistical models, machine learning algorithms and big data solutions to automatically scale Amazon’s compute infrastructure, optimizing the balance between availability risk and cost efficiency for all of Amazon businesses. Key job responsibilities - Process and analyze large data sets, mining additional data sources as needed - Build statistical models and drive scalable solutions for multi-year capacity demand forecasting horizons - Create, enhance, and maintain technical documentation, and present to other scientists and business leaders - Process and analyze large-scale operational data to identify patterns and inform model development - Create, enhance, and maintain technical documentation, and present research findings to scientists, engineering teams, and senior leadership
US, WA, Redmond
At Amazon, we’re inventing on behalf of customers, and with Amazon Leo, we’re redefining what global connectivity looks like. Our mission is to deliver fast, affordable broadband to unserved and underserved communities around the world through a constellation of low Earth orbit (LEO) satellites. Every system we build helps connect people to education, healthcare, opportunity, and each other. As a Data Scientist, you will be responsible for developing advanced analytics and machine learning solutions for user terminals. You will develop predictive models to proactively identify possible user terminal failures in the field. You will work in a collaborative environment with a multi-disciplinary team, including constellation, RF, antenna, silicon, algorithm, and software engineers. Key job responsibilities As a Data Scientist, you will develop analytic tools for a team developing current and future user terminals. Your responsibilities include: • Develop statistical and analytical tool to enable the regression decision from on-orbit and lab measurement of user terminals • Publish documents and create compelling visualizations and presentations to communicate insights to stakeholders • Create and manage datasets for continued pre-training and supervised fine-tuning of LLMs • Develop scalable visualizations for analysis of user terminal performance • Work closely with constellation, RF, antenna, silicon, algorithm, and software engineers to root-cause the failures using data as the primary tool • Drive consensus on metrics and analysis approaches to support product development strategy Export Control Requirement: Due to applicable export control laws and regulations, candidates must be a U.S. citizen or national, U.S. permanent resident (i.e., current Green Card holder), or lawfully admitted into the U.S. as a refugee or granted asylum. A day in the life As a Data Scientist in the LEO Customer Terminal Team, you will work daily with satellite constellation, algorithm, RF, antenna, silicon, hardware, and software teams in a collaborative environment. Your focus will be using data as an intelligence source to enable design decisions for the team. About the team The LEO Customer Terminal team is responsible for developing both outdoor and indoor devices that enable customers to access internet service via the LEO satellite network. We own the entire process from early prototypes through mass production, including requirements documentation, architecture definition, hardware development, algorithm development, and all integration and verification testing.
US, CA, Irvine
Do you want to write the algorithms that control next-generation batteries, and shape the future of energy storage? This role sits where electrochemistry, data/ML, and control theory meet. You will develop the physics-informed and data-driven methods that estimate state of charge, health, power capability, and remaining life, and validate them against lab and fleet data until they are ready to ship. Your algorithms will decide how hard a battery can be pushed, when it needs attention, and how long it will last, so they shape the safety, warranty, and economics of the whole product. You will work side by side with cell, systems, and software engineers, and as an early hire you will help define how we develop and validate battery algorithms. This role can be based in Boston, Irvine, Sunnyvale, or Seattle, and involves occasional domestic and international travel, up to 10% of the time. Key job responsibilities • Develop and own algorithms for state of charge, state of health, power capability, and remaining useful life, combining physics-based models with data-driven and estimation methods. • Deliver validated reference implementations, test vectors, and accuracy targets that define what production code must achieve. • Design the test plans and data needed to develop and validate algorithms, working with the cell and testing teams to turn lab and field data into model improvements. • Analyze algorithm performance across the deployed fleet, find where models drift or fail, and drive improvements. • Own the accuracy and robustness of battery algorithms, and sign off that production implementations match the validated reference. Provide algorithm evidence for safety certification. A day in the life Your week moves between data, models, and experiments. One day you might be working out why a health estimate drifts on cells that have aged in the field, and the next deciding which model structure holds accuracy at cold temperatures. You could be designing a test with the cell team to expose a behavior your model misses, or reviewing an implementation with an applied scientist to confirm that what ships matches what you validated. You will regularly share results with software, systems, and cell leaders, and your findings will shape decisions well beyond the algorithm itself. About the team We are building Amazon's energy storage capability, providing power for advanced technologies while contributing to a stable grid. Our product is highly connected, yet secure and resilient by design. We own it end to end, from software, ML, and controls through system design to cell selection and supply, and on to a safety-certified product in the field. The organization operates like a startup inside Amazon: small, fast-moving, and accountable for our decisions. We work across hardware, software, and science, with suppliers and partners worldwide, and with Amazon infrastructure, procurement, legal, and finance. The organization is at an early stage and growing quickly. You will be among the first algorithm hires, so you will help shape how we design, build, certify, and ship, with a direct line of sight to the product and business decisions your work informs. This is a dynamic role that will regularly present new challenges as the product and organization evolve.
US, CA, San Francisco
The Amazon Center for Quantum Computing (CQC) is seeking an Applied Scientist to research and design cryogenic control hardware for large-scale quantum processors, with an emphasis on superconducting digital circuits. Controlling and reading out orders of magnitude more qubits than today's systems demands rethinking where classical control lives and what technology implements it; you will design and model superconducting digital logic (e.g., single-flux-quantum-family circuits) and related cryogenic electronics, evaluate them against the wiring, power, and thermal budgets of a scaled system, and co-design control approaches with the qubit devices they serve. You will carry designs from concept through simulation, layout, design review, and fabrication handoff, and your evaluations will inform which control-electronics directions the organization invests in. Key job responsibilities • Design and simulate superconducting digital circuits and cryogenic control/readout electronics for scalable qubit control • Develop and validate Josephson-junction circuit models, timing and margin analyses, and verification methodology for superconducting digital designs • Quantify system-level trade-offs — wiring count, power dissipation at each cryogenic stage, latency, footprint — across candidate control architectures, and communicate recommendations • Co-design control interfaces with qubit-device colleagues so control electronics and quantum devices are developed as one system • Deliver design artifacts through the organization's design-request and design-review processes, including tapeout-ready layouts and verification reports • Present results internally and, where appropriate, publish in peer-reviewed venues About the team The Enabling Technologies team develops technologies and relationships facilitating scaling, including alternative quantum processor architectures, superconducting qubit device packaging, and cryogenic control device electronics. We work alongside a co-located quantum processor design team focused on current-generation devices; the two teams share design and review processes, and moving ideas between them is an explicit part of our charter.
US, WA, Redmond
Amazon Leo is building a constellation of thousands of low Earth orbit satellites. It will bring fast, reliable internet to customers beyond the reach of existing networks. On the Guidance, Navigation and Control (GNC) team, you will design the algorithms, simulations and onboard autonomy that keep every satellite precisely pointed and stable. Your work lets the payload serve customers on the ground, and it keeps the fleet flying safely. This is satellite GNC at constellation scale. The constellation is launching and growing today, so you will see your work go from concept to orbit, and then fly on many satellites. In this role, you will: - Take your GNC algorithms from concept to orbit, and stay with them through integration, test and on-orbit operations. - Write the production C++ flight code for your own algorithms. The code that flies is the code you write. - Solve hard problems in precise pointing, payload cueing and fleet autonomy. - Work across design, simulation, test and flight operations, not a narrow slice of the lifecycle. **Export Control Requirement:** Due to applicable export control laws and regulations, candidates must be a U.S. citizen or national, U.S. permanent resident (i.e., current Green Card holder), or lawfully admitted into the U.S. as a refugee or granted asylum. Key job responsibilities - Design and analyze algorithms for state estimation, attitude determination and control, precise pointing and payload cueing against demanding performance requirements. - Implement these algorithms in production C++ flight software. Our GNC engineers own their algorithms all the way into flight, and partner with our embedded software engineers to integrate and test them. - Write concepts of operations for each phase of a satellite's life, from launch and orbit raising to service and deorbit, including failures and recovery. Balance what the payload needs against momentum, power, thermal and ground-contact limits. - Develop momentum management strategies with reaction wheels and magnetic torquers. Help select, size and place the GNC sensors and actuators for future satellites, and design the algorithms that use them. These include star trackers, magnetometers, sun sensors, IMUs and GNSS receivers. - Develop onboard autonomy, including Fault Detection, Isolation and Recovery (FDIR), so that the fleet operates safely at scale with minimal ground intervention. - Build and validate satellite and constellation models and simulations at several levels of fidelity, including 6-DOF simulation and Monte Carlo analysis. Verify closed-loop performance in hardware-in-the-loop (HITL) tests. - Support component environmental tests, functional and performance checkout, and subsystem and satellite integration in our labs. - Analyze telemetry from the whole fleet. Build the metrics, dashboards and tools that track pointing performance and payload operations time as the constellation grows, and use them to improve the fleet. - Operate the GNC system on orbit and take part in the team's on-call rotation. Review fleet data, support maneuvers, and resolve anomalies when on-orbit behavior differs from the ground model. - Review designs and code with the team, and document your algorithms, analyses and results clearly. A day in the life This role covers a wide range of problems across the spacecraft and the network. You will derive and prototype estimation and control algorithms, and then turn them into production flight code. You will prove them in 6-DOF and Monte Carlo simulation and in hardware-in-the-loop tests in the lab. You will support satellite integration. When a satellite does not behave as the ground model predicted, you will dig into fleet telemetry, find the cause and drive the fix. You will own each problem end to end, with the focus to go deep on it. GNC is at the center of safe flight, so you will work across the whole program. The payload, power, thermal and operations teams all depend on GNC, and you will balance their needs against the pointing and momentum budgets. You will partner closely with avionics, flight software and embedded software engineers to make your algorithms run reliably on the spacecraft. You will help the mechanical teams shape the next generation of satellite hardware, from reaction wheels to star trackers. As satellites move from design through manufacturing into orbit, you will work with systems engineering and Assembly, Integration and Test. The problems are hard: tight pointing requirements, a large constellation to keep flying safely, and the chance to invent capabilities that do not exist yet. Constant work with other teams makes this a place where you keep learning and growing. About the team You will join the Satellite Attitude Determination and Control team. We own GNC for our satellites end to end: algorithm design, flight software, lab integration, and flight operations of our own satellites on orbit. Our engineers bring deep experience from many satellite programs and other flight vehicles, with real strength in both our mission and the core GNC disciplines. We design, prototype, test, iterate and learn together. Because GNC is central to safe flight, we drive the concepts of operations and many of the system-level analyses on the program. We also have a lot of freedom. We trust our engineers to choose their own tools and approaches for the problems they face, and to own the results. If you want the autonomy to solve hard problems your way, with a team of strong engineers, you will feel at home here.
US, WA, Redmond
Amazon Leo is building a constellation of thousands of low Earth orbit satellites. It will bring fast, reliable internet to customers beyond the reach of existing networks. On the Guidance, Navigation and Control (GNC) team, you will design the algorithms, simulations and onboard autonomy that keep every satellite precisely pointed and stable. Your work lets the payload serve customers on the ground, and it keeps the fleet flying safely. This is satellite GNC at constellation scale. The constellation is launching and growing today, so you will see your work go from concept to orbit, and then fly on many satellites. In this role, you will: - Take your GNC algorithms from concept to orbit, and stay with them through integration, test and on-orbit operations. - Write the production C++ flight code for your own algorithms. The code that flies is the code you write. - Solve hard problems in precise pointing, payload cueing and fleet autonomy. - Work across design, simulation, test and flight operations, not a narrow slice of the lifecycle. **Export Control Requirement:** Due to applicable export control laws and regulations, candidates must be a U.S. citizen or national, U.S. permanent resident (i.e., current Green Card holder), or lawfully admitted into the U.S. as a refugee or granted asylum. Key job responsibilities - Design and analyze algorithms for state estimation, attitude determination and control, precise pointing and payload cueing against demanding performance requirements. - Implement these algorithms in production C++ flight software. Our GNC engineers own their algorithms all the way into flight, and partner with our embedded software engineers to integrate and test them. - Write concepts of operations for each phase of a satellite's life, from launch and orbit raising to service and deorbit, including failures and recovery. Balance what the payload needs against momentum, power, thermal and ground-contact limits. - Develop momentum management strategies with reaction wheels and magnetic torquers. Help select, size and place the GNC sensors and actuators for future satellites, and design the algorithms that use them. These include star trackers, magnetometers, sun sensors, IMUs and GNSS receivers. - Develop onboard autonomy, including Fault Detection, Isolation and Recovery (FDIR), so that the fleet operates safely at scale with minimal ground intervention. - Build and validate satellite and constellation models and simulations at several levels of fidelity, including 6-DOF simulation and Monte Carlo analysis. Verify closed-loop performance in hardware-in-the-loop (HITL) tests. - Support component environmental tests, functional and performance checkout, and subsystem and satellite integration in our labs. - Analyze telemetry from the whole fleet. Build the metrics, dashboards and tools that track pointing performance and payload operations time as the constellation grows, and use them to improve the fleet. - Operate the GNC system on orbit and take part in the team's on-call rotation. Review fleet data, support maneuvers, and resolve anomalies when on-orbit behavior differs from the ground model. - Review designs and code with the team, and document your algorithms, analyses and results clearly. A day in the life This role covers a wide range of problems across the spacecraft and the network. You will derive and prototype estimation and control algorithms, and then turn them into production flight code. You will prove them in 6-DOF and Monte Carlo simulation and in hardware-in-the-loop tests in the lab. You will support satellite integration. When a satellite does not behave as the ground model predicted, you will dig into fleet telemetry, find the cause and drive the fix. You will own each problem end to end, with the focus to go deep on it. GNC is at the center of safe flight, so you will work across the whole program. The payload, power, thermal and operations teams all depend on GNC, and you will balance their needs against the pointing and momentum budgets. You will partner closely with avionics, flight software and embedded software engineers to make your algorithms run reliably on the spacecraft. You will help the mechanical teams shape the next generation of satellite hardware, from reaction wheels to star trackers. As satellites move from design through manufacturing into orbit, you will work with systems engineering and Assembly, Integration and Test. The problems are hard: tight pointing requirements, a large constellation to keep flying safely, and the chance to invent capabilities that do not exist yet. Constant work with other teams makes this a place where you keep learning and growing. About the team You will join the Satellite Attitude Determination and Control team. We own GNC for our satellites end to end: algorithm design, flight software, lab integration, and flight operations of our own satellites on orbit. Our engineers bring deep experience from many satellite programs and other flight vehicles, with real strength in both our mission and the core GNC disciplines. We design, prototype, test, iterate and learn together. Because GNC is central to safe flight, we drive the concepts of operations and many of the system-level analyses on the program. We also have a lot of freedom. We trust our engineers to choose their own tools and approaches for the problems they face, and to own the results. If you want the autonomy to solve hard problems your way, with a team of strong engineers, you will feel at home here.
US, WA, Seattle
Do you want to make AI provably correct for chip design and verification? We're hiring an Applied Scientist to combine large language models with formal methods such as Lean 4 and turn AI from a helpful assistant into a trusted engineering tool for silicon. Our team builds the formal verification methods behind custom silicon at Amazon scale. As AI agents take on more of chip design and verification, we need people who can make sure their output is checkable, sound and grounded in mathematics. You will research and build systems where LLMs work alongside interactive theorem provers, SMT solvers and model checkers. Engineers write the specifications. AI refines them against RTL, generates proof steps and closes proofs at machine speed. Every result is checked by a formal kernel, not trusted on faith. Work at the frontier of AI reasoning, theorem proving and hardware verification Ship solutions that directly affect real chips running in AWS data centers Publish and help shape how the industry formalizes AI use in hardware engineering Key job responsibilities Design and build LLM-driven systems for formal verification and design tasks, including proof generation, invariant and lemma discovery, spec-to-RTL refinement, and counterexample analysis Develop frameworks in Lean 4 (and related tools such as SMT solvers, model checkers and commercial FV engines) that formally check AI-generated artifacts, so they are correct by construction rather than just plausible Formalize hardware semantics, ISAs and microarchitectural properties in Lean 4 to create machine-checkable foundations for AI agents to reason over Track and evaluate state-of-the-art AI work (LLM agents, autoformalization, neural theorem proving, reinforcement learning from proof feedback) and turn promising research into production tools Build benchmarks and evaluation methods that measure AI soundness, proof success rate and engineering impact on real designs Partner with FV and design engineers to find the highest-leverage problems and deploy solutions into active chip programs Publish research, file patents and represent Amazon in the formal methods and AI communities Mentor engineers and scientists on applying formal AI methods
US, MA, North Reading
Robotics Applied Scientist II Intern/Co-op (2027) Are you passionate about robotics and research? Do you want to solve real customer problems through innovative technology? Do you enjoy working on scalable research and projects in a collaborative team environment? Do you want to see your science solutions directly impact millions of customers worldwide? We’re looking for current PhD students with a passion for robotic research and applications to join us in 2027 as Robotics Applied Scientist II Interns/Co-ops to shape the future of robotics and transform automation at Amazon’s scale. By applying to this role, you will be considered for Robotics Applied Scientist II Intern/Co-op (2027) opportunities across various Robotics teams at Amazon with different robotics research focus. Internship positions are available for multiple locations, durations (3 to 6+ months), and year-round start dates (winter, spring, summer, fall). Join us at the forefront of Applied Science, where your contributions will shape the future of Robotics! Key job responsibilities As a Robotics Applied Scientist II Intern/Co-op, you will work alongside global experts to advance the state of the art in robotics and artificial intelligence, tackling innovative problems that bridge the gap between research and real-world robotics implementation to innovate and build solutions on behalf of our customers. We are particularly interested in students with specialization and expertise in one or more of the following research areas: - Robotics - Artificial Intelligence - Robotics Manipulation (e.g., robot arm, grasping, dexterous manipulation, end of arm tools/end effector) - Autonomous Mobile Robots - Mobile Manipulation - Multi-Robot Coordination - Autonomous Navigation - Locomotion - Motion/Path Planning - Controls - Perception - Sensing - Robot Learning - Machine Learning - Computer Vision - Large Language Models (LLM), Vision-Language-Action Models (VLA), Vision-Language-Models (VLM) - World Models - Human-Robot Interaction - Robotics Simulation - Optimization - And related! Key responsibilities may include: - Develop novel, scalable algorithms and/or modeling techniques that advance the state-of-the-art in science areas such as robotics, artificial intelligence, or related - Tackle challenging, innovative research problems within robotics, artificial intelligence, or related that bridge the gap between theoretical advancement and practical robotics implementation - Collaborate with cross-functional teams to solve complex problems, and to communicate research findings clearly, leveraging your expertise in robotics, artificial intelligence, or related - Demonstrate the ability to work independently, thrive in a fast-paced, ever-changing environment - Leverage AI-powered tools where applicable to accelerate research, experimentation, and prototyping. - Critically review and validate outputs from AI tools and automated systems. About the team Explore Robotics Teams at Amazon At Amazon, robotics is where innovative research meets real-world deployment. There are many different specialized robotics teams, including the few highlighted below. Learn more about Robotics at Amazon here: https://www.amazon.science/research-areas/robotics Fulfillment Technologies and Robotics We build dynamic partnerships between people and intelligent machines. This intricate collaboration helps Amazon fulfill orders with unmatched accuracy. Working in symphony with our robotic technology, you’ll have the opportunity to extend your technical capabilities by working alongside some of the industry’s most advanced technologies. This includes our fleet of autonomous mobile robots, sophisticated control software, and technologies like language perception, machine learning, object recognition, and semantic understanding of commands. These technologies help us deliver an ever-improving customer and employee experience, as well as improve the safety of our facilities. Amazon Robotics Amazon Robotics is at the epicenter of robotics innovation. We design, test, and build mobile robots and mechatronic systems. Our offices, labs, test floors, and factories are close together, which means we can design the hardware, write the code, test, build, and watch it all come to life. Our areas of focus include advancements in autonomous mobility, AI, robotic management software, and much more. Fauna Fauna is focused on building capable, safe, and genuinely delightful robots for everyday life. Fauna’s goal is simple: make robots people actually want to live and interact with everyday. Fauna develops tightly integrated hardware and software systems that make it faster, safer, and more intuitive to create real-world robotic products. Fauna’s work spans the full stack: mechanical design, control systems, dynamic modeling, and intelligent software. The focus is not just functionality, but overall experience. Amazon Fulfillment Technologies Amazon Fulfillment Technologies develops tech solutions that create network optimizations for all Amazon sites worldwide. We own network infrastructure and devices in all buildings and labor planning and scheduling technology for fulfillment centers in North America and Europe.
US, CA, Pasadena
We are seeking Applied Scientists to join Amazon. In this role, you will develop and deploy the science of safe autonomy on highly dynamic robots, advancing the frontier through both foundational research and realization on hardware. You will contribute to achieving safe autonomy across three key areas: control barrier function (CBF) theory for robust and performant safety on hardware; safe reinforcement learning for agile whole-body control; and layered safety filters that interface with learning, perception, and semantic reasoning systems. You will validate your work experimentally on state-of-the-art robotic platforms — removing bottlenecks to deployment and enabling robots to safely operate around humans. You will work with the inventor of CBFs, as well as top scientists and engineers at Amazon developing the next generation of safe autonomy. Key job responsibilities -Advance the science of safe autonomy from formal foundations to the integration with learning and perception to validation on hardware — with particular emphasis on methods that bridge these domains. -Test and validate hardware, with a focus on next generation robotic systems. Including locomotion, manipulation and loco-manipulation. -Leverage the deployments on hardware to validate the underlying science, identifying gaps between theory and practice that drive the next cycle of research. hardware to validate the underlying science, identifying gaps between theory and practice that drive the next cycle of research. -Publish research at top-tier robotics, control, and ML venues, and contribute to Amazon’s scientific reputation in advanced robotics. -Collaborate with SAF Lab and Amazon production teams to move research into robots deployed at Amazon scale. A day in the life Amazon offers a full range of benefits that support you and eligible family members, including domestic partners and their children. Benefits can vary by location, the number of regularly scheduled hours you work, length of employment, and job status such as seasonal or temporary employment. The benefits that generally apply to regular, full-time employees include: -Medical, Dental, and Vision Coverage -Maternity and Parental Leave Options -Paid Time Off (PTO) -401(k) Plan If you are not sure that every qualification on the list above describes you exactly, we’d still love to hear from you! At Amazon, we value people with unique backgrounds, experiences, and skillsets. If you’re passionate about this role and want to make an impact on a global scale, please apply! About the team The Safe Autonomy Frontiers (SAF) Lab is the first industry research lab dedicated to safe autonomy, founded by the inventor of control barrier functions. We are developing a universal safety layer for the next generation of robotic systems: mobile robots, manipulators, quadrupeds, and humanoids. Here you will advance performant safety for highly dynamic robots — CBF theory integrated with perception and learning, evaluated on next-generation platforms — and your work will underpin robots operating alongside people at Amazon’s unprecedented scale.
US, NY, New York
About Sponsored Products and Brands: The Sponsored Products and Brands (SPB) organization at Amazon Ads is re-imagining the advertising landscape through industry leading generative AI technologies, revolutionizing how millions of customers discover products and engage with brands across Amazon.com and beyond. We are at the forefront of re-inventing advertising experiences, bridging human creativity with artificial intelligence to transform every aspect of the advertising lifecycle from ad creation and optimization to performance analysis and customer insights. We are a passionate group of innovators dedicated to developing responsible and intelligent AI technologies that balance the needs of advertisers, enhance the shopping experience, and strengthen the marketplace. If you're energized by solving complex challenges and pushing the boundaries of what's possible with AI, join us in shaping the future of advertising. About Our Team: The Brand Beacon team is responsible for inventing impressions offerings for brands to increase share of voice via premium experiences, helping brands get discovered, acquire new customers and sustainably grow customer lifetime value. We build end-to-end solutions that enable brands to drive discovery, visibility and share of voice. This includes building advertiser controls, shopper experiences, monetization strategies and optimization features. We succeed when (1) shoppers discover, engage and build affinity with brands and (2) brands can grow their business at scale with our advertising products. About This Role: As an Applied Scientist on our team, you will: * Develop AI solutions for advertiser and shopper experiences. Build monetization and optimization systems that leverage generative models to value and improve campaign performance. * Define a long-term science vision and roadmap for our Brand Beacon advertising business, driven from our customers' needs, translating that direction into specific plans for applied scientists and engineering teams. This role combines science leadership, organizational ability, technical strength, product focus, and business understanding. * Design and conduct A/B experiments to evaluate proposed solutions based on in-depth data analyses. * Effectively communicate technical and non-technical ideas with teammates and stakeholders; * Stay up-to-date with advancements and the latest modeling techniques in the field. * Think big about the arc of development of Gen AI over a multi-year horizon and identify new opportunities to apply these technologies to solve real-world problems. #GenAI