Sense, Act, and Scale
The path to improving building energy efficiency can be paved with the framework of sense, act, and scale say authors Bharathan Balaji, an Amazon senior research scientist within the company's Devices organization, and Rob Aldrich, an Amazon Web Services senior sustainability strategist.

Creating sustainable, data-driven buildings

As office buildings become smarter, it is easier to configure them with sustainability management in mind.

Editor’s note: This article is adapted from a keynote presentation Bharathan Balaji , an Amazon senior research scientist within the company’s Devices organization, delivered in June at the 17th International Conference on Intelligent Environments . It is further informed by the book "IP-Enabled Energy Management, A Proven Strategy for Administering Energy as a Service " and its author, Rob Aldrich, Amazon Web Services senior sustainability strategist.

Buildings generate about 28% of the global greenhouse gas emissions today. The United Nations Global Status Report projects that buildings need to be at least 30% more energy efficient to achieve Paris Agreement goals.

How can we achieve that 30% energy efficiency target?

The path to reducing our emissions by improving building energy efficiency can be paved with the framework of sense, act, and scale. We need to sense to ascertain efficiency gaps within buildings. We need solutions that act on the information to achieve energy savings. And finally, we need to scale solutions so they get implemented broadly. Here is how this proposed framework can help us achieve our goals.

Sense

For office buildings that are smart and connected, the data set is rich and has much of the granular, sustainability data needed to drive change. Electricity and gas meters tell us how much energy is being consumed by a building, occupancy sensors tell us the number of people in the building, and temperature sensors tell us how much energy we need to cool a room. Sensors are the source of our information and the key to unlocking energy efficiency gaps. Even simple dashboards with such data can motivate users to save energy.

These types of sensors are abundant in modern buildings. However, many of them are wired sensors that are part of the building’s original design, and it is expensive to modify or install new sensors. Office buildings have a life of 50+ years, and sensor technology advances far more rapidly. Wireless sensors undoubtedly reduce communications costs, but they still need to be powered through wires, or use batteries that significantly increase maintenance costs at scale (imagine changing the batteries in every room of an office building).

New sensor options provide for ambient energy harvesting. These wireless sensors work by scavenging energy from the environment such as using ambient light, ventilation air flow, or hot water pipes. These sensors can minimize both energy and communications costs, but scavenged energy is insufficient to sense 24x7. We can improve reliability by predicting the environmental patterns and judiciously using the available energy.

A recent paper in SenSys (coauthored by Bharathan, lead author of this article) showed that reinforcement-learning-based scheduling of energy harvesting sensors can detect 93% of events in a real-world deployment. While the small percentage of missed events make these sensors ineligible for use in essential services, we can use the data from these inexpensive sensors opportunistically to create a rich information layer that helps save energy.

Information Bottleneck: Senors

This new, rich information layer can drive the return on investment (ROI) that has been lacking in many sensor installations. Energy and data managers can provide the missing link between top-end sustainability initiatives and the many different sensor options that exist in buildings. Furthermore, the cost of sensor architectures can be reduced by focusing only on the key data sources that support a given use case. 

For this article we chose to focus primarily on building sustainability data: energy, occupancy, emissions, air and water. This focus helps enable an estimated ROI because you already have a use case that defines how you will act on the information available. The use case for sustainability is to reduce wasted energy while moving to low greenhouse gas (GhG) fuel sources.  Informed by sensor data, the actions taken in support of these goals can be the mechanism by which savings are achieved.

Act

The traditional way to make buildings more energy efficient is to inspect the equipment, install sensors to measure baseline energy consumption, fix faults, upgrade equipment, and optimize equipment configuration. Heating, ventilation and air conditioning (HVAC) systems typically comprise the largest portion of building energy use, and many of the efficiency measures target HVAC improvements. These methods work, and can lead to more than 10% reductions in building energy use. The entire process is often referred to as building retrofitting through performance contracting.

However, two issues with the above approach typically block adoption. First, there is an upfront cost to hire experts and upgrade equipment. The ROI can take years. Second, there is limited scope for innovation beyond the template followed during commissioning. Building innovation is stifled by vertically integrated systems and an inability to easily deploy third-party applications. One of the primary reasons for the explosive growth in the computing industry is a standard interface and ease of application installation. An analogous system for buildings will create new opportunities to save energy. The innovation opportunities with a standardized building information system is highlighted with three use cases below. It is easy to create such a system with current technologies; the figure below shows a high-level architecture.

Building information system architecture

Occupancy-based control

The idea is simple: if we shut off systems that aren’t required when people aren’t present, we save energy. However, detecting occupancy reliably in a privacy-preserving manner is challenging, and most buildings today keep the lights (and HVAC) on even when no one is present. A paper published in SenSys (coauthored by Bharathan) showed that it is possible to infer occupancy using WiFi data, building floor plans, and personnel office room assignments. Among the study participants, peak building occupancy was just 60% (see figure below), and occupancy-based control saved 18% of HVAC electricity use by controlling one-quarter of the building area. The proposed solution simply leverages existing building infrastructure and is inexpensive to deploy. This type of solution is possible only because the information across different systems is exchanged freely.

Building Occupancy Trends

Fault detection

Fixing faults is core to building maintenance, but it is challenging to identify energy-wasting faults as they are difficult to notice, unlike a leak or an uncomfortable temperature. Typical building-fault detection relies on protocols established by experts, but these rules do not provide sufficient prioritization information, nor how much energy they waste.

Sophisticated fault detection algorithms have been published in literature, yet these are not deployed in practice because of vendor- locked systems. Using one year of building data, researchers (Bharathan was a coauthor) developed a simple machine learning algorithm that looks for rooms that do not follow typical temperature patterns. The algorithm identified 88 faults within the building’s HVAC system after an expert fixed all the faults found during an inspection. Many of these faults had existed for years, and resulted in estimated 410.3MWh/year savings. Again, the key component to this solution: easy access to building data.

Software thermostat

The thermostat is the only interface between building occupants and the energy-intensive HVAC system. And yet, in most buildings, occupants don’t know where the thermostat is or how to use it. The HVAC system’s primary function is to keep occupants comfortable so that they can be productive. But without thermostat feedback, occupants can end up being uncomfortable and waste energy.

With the building information system, researchers (Bharathan and collaborators) built a software version of the thermostat to address these concerns (screenshot below). The application was an instant hit and remains popular eight years after its launch. The resulting user study published in Ubicomp showed that users were frustrated with the old thermostat. In fact, one user actually taped a manila envelope on the vent to stop cold air from blowing. The software thermostat helped users precisely control their environment and send complaints if needed. The HVAC maintenance personnel were worried that the interface would lead to a flood of complaints that they weren’t staffed to handle. Usage data showed that most users were happy to use the application without giving any feedback. The few complaints received led to identification of major faults, such as a thermostat being blocked by a computer.

Software thermostat

The three use cases above didn’t require additional sensor installations and simply leveraged existing information. With low-cost solutions, we can attract building owners to adopt solutions that save energy. But we need additional incentives within the building industry to create these low-cost solutions that can have large-scale impact.

These use cases demonstrate that sustainable design doesn’t stop at the brick and mortar of the building. It should carry through to how the energy, emissions, air, water and waste can be managed as systems across buildings. As companies worldwide embark on making their buildings more sustainable, it will be critical to have a data-driven measure of success. The sense and act steps allow each company to look at what is common in the data model today, get started, assess the value, and scale as needed using open-source tools.

Scale

Even when an attractive energy-saving solution is available, it is difficult to deploy the solution at scale. This is because each building is unique, from its infrastructure and how it is used, to the software used to manage daily operations, and how it changes over time. While the fundamental components of a building remain the same (e.g., rooms, smoke sensors, ventilation fans), each vendor treats them differently. When we try to deploy a solution to a building, the discrepancies between vendor representations become difficult to resolve automatically.

In the computing industry, on other hand, it is easy for us to install an application without worrying about the manufacturer or provider because of the use of specifications (e.g., standard protocols for WiFi) and programming interfaces (e.g., Android OS for the phone). Researchers (including Bharathan) created such a standard interface for buildings with the Brick schema, where the building components and their connections to each other are represented through a knowledge graph. The figure below shows a Brick representation of a toy building with two rooms and a few sensors. Brick is now an industry consortium with growing demand, and is in the process of being integrated into building standards.

Given a standard representation such as Brick, we still have the task of representing the existing building in this new format, which can take manual effort and be slow to deploy. Using machine-learning techniques in natural language processing, we can automate this translation and minimize manual effort. The algorithm’s performance improves as more buildings are mapped to Brick and it learns from representation patterns across buildings.

The Brick schema

With the sense, act and scale framework, we envision a day when it will be as easy to configure a building as it is our phones today. We can improve the information available to building managers by using low-cost sensors, use the available information to develop innovations that save energy, and deploy the solution to many buildings with use of a knowledge graph.

Getting started

We are seeing early success in using the sense, act, scale approach in our AWS Sustainability Services practice to optimize how buildings report their sustainability data through the cloud.  It solves several problems by providing a simple framework to plan how our top-level sustainability strategy can be supported by specific building-optimization steps, underpinned by a semi-standardized data model.

The lack of standardization across building management systems has resulted in difficulties in accessing the data. Now that those data acquisition problems are being solved through advances in IoT and API, it opens up new opportunities to expose, analyze and report data that was previously difficult or costly to acquire.  With new advances like the Brick schema, we are making advances in how we can manage building assets at scale, just like servers, laptops and phones.

We are starting to see the potential to move the world from a building management systems approach; one building, one manager to a building systems management approach; many buildings, one manager. Energy efficiency gains of 30% or more are more feasible when we automate energy-control policies across all buildings at the push of a button.

Research areas

Related content

US, CA, Sunnyvale
The Region Flexibility Engineering (RFE) team builds and leverages foundational infrastructure capabilities, tools, and datasets needed to support the rapid global expansion of Amazon's SOA infrastructure. Our team focuses on robust and scalable architecture patterns and engineering best practices, driving adoption of ever-evolving and AWS technologies. RFE is looking for a passionate, results-oriented, inventive Data Scientist to refine and execute experiments towards our grand vision, influence and implement technical solutions for regional placement automation, cross-region libraries, and tooling useful for teams across Amazon. As a Data Scientist in Region Flexibility, you will work to enable Amazon businesses to leverage new AWS regions and improve the efficiency and scale of our business. Our project spans across all of Amazon Stores, Digital and Others (SDO) Businesses and we work closely with AWS teams to advise them on SDO requirements. As innovators who embrace new technology, you will be empowered to choose the right highly scalable and available technology to solve complex problems and will directly influence product design. The end-state architecture will enable services to break region coupling while retaining the ability to keep critical business functions within a region. This architecture will improve customer latency through local affinity to compute resources and reduce the blast radius in case of region failures. We leverage off the sciences of data, information processing, machine learning, and generative AI to improve user experience, automation, service resilience, and operational efficiency. Key job responsibilities As an RFE Data Scientist, you will work closely with product and technical leaders throughout Amazon and will be responsible for influencing technical decisions and building data-driven automation capabilities in areas of development/modeling that you identify as critical future region flexibility offerings. You will identify both enablers and blockers of adoption for region flex, and build models to raise the bar in terms of understanding questions related to data set and service relationships and predict the impact of region changes and provide offerings to mitigate that impact. About the team The Regional Flexibility Engineering (RFE) organization supports the rapid global expansion of Amazon's infrastructure. Our projects support Amazon businesses like Stores, Alexa, Kindle, and Prime Video. We drive adoption of ever-evolving and AWS and non-AWS technologies, and work closely with AWS teams to improve AWS public offerings. Our organization focuses on robust and scalable solutions, simple to use, and delivered with engineering best practices. We leverage and build foundational infrastructure capabilities, tools, and datasets that enable Amazon teams to delight our customers. With millions of people using Amazon’s products every day, we appreciate the importance of making our solutions “just work”.
US, WA, Seattle
The Sponsored Products and Brands team at Amazon Ads is re-imagining the advertising landscape through 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. We are looking for an Applied Scientist to build the science that helps Amazon's advertisers grow — with a focus on Cross Border Sellers who face distinct barriers as they scale across multiple marketplaces, and this role is about understanding those pain points deeply and removing them: building intelligent, autonomous solutions that simplify advertising, act efficiently on the advertiser's behalf, and let advertisers accelerate their growth and success. We expect Scientist to think innovatively about how to reduce the effort and complexity of advertising for these advertisers. Working backwards from their needs — spanning hands-off sellers and global brands with cross-marketplace operations — you will take the lead on medium-to-large, ambiguous problems where neither the problem nor the solution is well defined, invent new methods, validate them through rigorous experimentation, and deliver customer-facing products with measurable business impact. This role combines science depth, product focus, and hands-on engineering: you will raise the science bar, build consensus on approach across product and engineering partners, and mentor scientists and engineers while remaining deeply hands-on with the hardest technical problems. Key job responsibilities As an Applied Scientist on this team you will: - Understand the pain points of Cross border advertisers as they scale across marketplaces, and build science-driven solutions that remove barriers and accelerate their growth and success. - Build agentic and ML systems that autonomously create, structure, and manage ad campaigns on advertisers' behalf, encoding auction and marketplace dynamics (bidding, budget pacing, targeting decisions) while balancing advertiser ROI, shopper experience, and marketplace health. - Innovate on new, simpler ways to advertise powered by GenAI, and push the frontier of existing autonomous programs (e.g., auto-targeting, global lift-and-shift) while proposing and prototyping the next generation of campaign automation. - Develop models across the campaign lifecycle — opportunity discovery, ranking, ad-readiness and demand prediction, and bid/budget optimization — and apply the right approach for each problem, from classical ML to LLM/reasoning methods. - Define and curate the datasets and signals needed to train and evaluate these systems — advertiser and campaign data, cross-marketplace performance, auction and bid/budget signals, impressions, clicks, conversions, and search-term/keyword performance. - Own core parts of the agentic architecture — planning, tool use and integration (e.g., MCP), reasoning frameworks (e.g., ReAct, CoT/ToT), and model customization — and define evaluation and safety methodology so that automated decisions are reliable and trustworthy. - Stay deeply hands-on: write production-quality, critical-path code and build core components that take systems from prototype to launch on large-scale pipelines (Spark/EMR, Airflow) and online serving. - Raise the science bar: review designs and experiment plans, and communicate results and tradeoffs clearly to technical and business leaders. About the team Autonomous SP drives growth and simplifies advertising for Amazon's hands-off advertisers by creating and enhancing autonomous campaign solutions. We lead existing successful programs, including auto-targeting and global lift-and-shift, and continually innovate by building new, simpler campaign constructs powered by GenAI to act efficiently on advertisers' behalf. Cross-border Seller Experience (CBSX) focuses on developing targeted solutions for domestic and global advertisers with multi-marketplace operations. By understanding and addressing their unique Seller Central needs, we optimize for cross-marketplace efficiency, improved performance, and streamlined advertising experiences. Our team operates horizontally, delivering impactful solutions that benefit both hands-on and hands-off advertisers globally. Together, we sit within Sponsored Products and Brands, which is re-imagining advertising through the latest generative AI — building responsible, intelligent systems that balance the needs of advertisers, the shopping experience, and marketplace health.
US, WA, Seattle
MULTIPLE POSITIONS AVAILABLE Employer: AMAZON WEB SERVICES, INC. Offered Position: Data Scientist III Job Location: Seattle, Washington Job Number: AMZ10593723 Position Responsibilities: Own the data science elements of various products to help with data-based decision making, product performance optimization, and product performance tracking. Work directly with product managers to help drive the design of the product. Work with Technical Product Managers to help drive the build planning. Translate business problems and products into data requirements and metrics. Initiate the design, development, and implementation of scientific analysis projects or deliverables. Own the analysis, modelling, system design, and development of data science solutions for products. Write documents and make presentations that explain model/analysis results to the business. Bridge the degree of uncertainty in both problem definition and data scientific solution approaches. Build consensus on data, metrics, and analysis to drive business and system strategy. Position Requirements: Master's degree or foreign equivalent degree in Statistics, Applied Mathematics, Economics, Engineering, Computer Science or a related field and two years of experience in the job offered or a related occupation. Employer will accept a Bachelor's degree or foreign equivalent degree in Statistics, Applied Mathematics, Economics, Engineering, Computer Science, or a related field and five years of progressive post-baccalaureate experience in the job offered or a related occupation as equivalent to the Master's degree and two years of experience. Must have one year of experience in the following skills: (1) building statistical models and machine learning models using large datasets from multiple resources; (2) building complex data analyses by leveraging scripting languages including Python, Java, or related scripting language; and (3) communicating with users, technical teams, and management to collect requirements, evaluate alternatives, and develop processes and tools to support the organization. Amazon.com is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation. 40 hours / week, 8:00am-5:00pm, Salary Range $166,036/year to $215,300/year. Amazon is a total compensation company. Dependent on the position offered, equity, sign-on payments, and other forms of compensation may be provided as part of a total compensation package, in addition to a full range of medical, financial, and/or other benefits. For more information, visit: https://www.aboutamazon.com/workplace/employee-benefits.#0000
US, WA, Seattle
Are you excited about using economic reasoning to shape decisions that affect millions of customers? Do you want to tackle ambiguous, high-impact problems where your analysis directly influences strategy and investment? We are looking for a Senior Economist to join Amazon and drive economic solutions for complex business challenges. In this role, you will define and prioritize analytical approaches, build rigorous econometric models, and translate findings into actionable recommendations for leadership. You will partner with engineers, product managers, scientists, and business leaders to deliver measurable outcomes. If you thrive on turning unstructured problems into clear, data-driven strategies, this is the role for you. Key job responsibilities - Lead the design, implementation, and delivery of economic analyses for complex or ambiguous business problems, providing strategic direction that informs organizational goals and investment decisions. - Develop and apply econometric models—including causal inference, structural estimation, and forecasting methods—choosing the right approach for each problem and validating results through rigorous testing. - Collaborate with cross-functional partners including engineers, product managers, and applied scientists to implement scalable solutions and translate economic insights into product and business improvements. - Communicate findings through clear narratives and technical documents for audiences ranging from peer economists to senior leaders, building consensus and influencing key decisions. - Evaluate and integrate generative AI tools where appropriate to augment research productivity, while mentoring other economists and raising the bar on analytical best practices across the team. A day in the life You might start your morning reviewing model performance metrics and refining an econometric specification before a working session with engineers on data pipeline requirements. After lunch, you could present preliminary findings from a causal analysis to business stakeholders, fielding questions and aligning on next steps. Later in the afternoon, you join a peer review for a fellow economist's research design, offering constructive feedback. Throughout the day, you balance hands-on analytical work with strategic conversations that connect your research to real business outcomes. About the team Our team of economists partners across Amazon to solve some of the company's most consequential business questions. We combine deep expertise in economic theory and applied econometrics with access to rich, large-scale data to deliver insights that shape long-term strategy. We value intellectual curiosity, collaborative problem-solving, and a commitment to rigorous science. If you are looking for an environment where your economic thinking directly drives impact at scale, we would love to hear from you.
US, WA, Redmond
Amazon Leo is building a low Earth orbit satellite broadband network to bring fast, affordable connectivity to customers worldwide. We're looking for a Senior Applied Scientist to invent the machine learning that will let the network predict, explain and prevent its own failures. You'll work on open research problems at large scale. These include anomaly detection on non-stationary, high-dimensional telemetry, causal root-cause inference over constantly changing satellite and ground network graphs, and trustworthy ML for operators making decisions under pressure. You'll own the science agenda, from forming hypotheses and designing new models to putting them into production systems that protect customer connectivity. 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 Define and lead a multi-year applied research agenda in network observability, anomaly prediction and availability modeling. Invent new time-series and spatio-temporal graph models, such as graph neural networks (GNNs), foundation models and dynamic baselining, to predict network and ground-segment failures before customers are affected. Develop causal inference and causal discovery methods for automated root-cause attribution across a large, interdependent event surface. Research probabilistic models that break availability and throughput into causal drivers (coverage, ground, network, terminal, payload, planning) and separate true signal from noise. Advance methods for alert correlation, deduplication, uncertainty quantification and metric-quality scoring. Explore large language models (LLMs) and agentic approaches for reasoning over telemetry, logs and incident narratives. Design rigorous offline and online evaluation, including backtesting against real closed incidents and gameday-based benchmarks. Take research into production on AWS (SageMaker, Bedrock), working with engineers on scalability, drift detection and explainability. Publish at top-tier venues, file patents and raise the scientific bar through mentoring and design reviews. A day in the life You might start the morning reading new literature on causal discovery and sketching how it applies to Leo's network graph. Later you could review a scientist's experiment design and debate the best evaluation methodology. During an event, you would test your attribution model live on the incident call. You might finish the day prototyping a new spatio-temporal anomaly detector and backtesting it against last quarter's incidents. About the team Amazon Leo Networking Software builds the software behind Leo's satellite and ground network. Our applied science team works on hard, open-ended problems with real-world impact. We value scientific rigor, curiosity and ownership, and we encourage publishing and contributing to the research community. As a Senior Applied Scientist, you'll help build this science function from the ground up and set the technical bar for the scientists who join after you.
US, WA, Bellevue
We are seeking a Senior Applied Scientist to push the state of the art in robot learning and help bring capable robots out of the lab and into everyday homes at Fauna Robotics. In this role, you will design novel algorithms across perception, manipulation, sim2real transfer, reinforcement learning, and multi-task learning, closing the gap between research and real-world deployment. You will work where robotics research meets production systems. You'll combine hands-on technical work with scientific leadership to guide the team toward the most promising directions. Working closely with software engineers and scientists, you will turn new ideas into robust solutions for dynamic, unstructured home environments. Homes bring challenges that structured settings like warehouses don't, and consumer-grade sensors and actuators have real limits, so this work calls for creative, out-of-the-box approaches. Key job responsibilities - Lead technical initiatives in areas such as robotics foundation models, reinforcement learning and manipulation - - Design experiments to identify the limitations of current state-of-the-art models and developing new models or techniques that can surpass these models - Design and implement novel deep learning architectures that push the boundaries of what robots can understand and accomplish - Mentor fellow scientists while maintaining strong individual technical contributions - Collaborate with engineering teams to optimize and scale models for real-world applications - Influence technical decisions and implementation strategies within your area of focus - Experienced in communicating complex technical work to a non-technical audience - The ability to work with minimal guidance, be proactive and to handle ambiguity and the challenge of quickly evolving goals About the team Fauna Robotics, an Amazon company, is building capable, safe, and genuinely delightful robots for everyday life. Our goal is simple: make robots people actually want to live and interact with in everyday human spaces. We believe that future won’t arrive until building for robotics becomes far more accessible. Today, too much effort is spent reinventing the fundamentals. We’re changing that by developing tightly integrated hardware and software systems that make it faster, safer, and more intuitive to create real-world robotic products. Our work spans the full stack: mechanical design, control systems, dynamic modeling, and intelligent software. The focus is not just functionality, but experience. We’re building robots that feel responsive, expressive, and genuinely useful. At Fauna, you’ll work at the frontier of this space, helping define how robots move, manipulate, and interact with people in natural environments. It’s an opportunity to solve hard problems across hardware and software with a team focused on making robotics accessible and joyful to build. If you care about making robotics real for everyone and building systems that are as delightful as they are capable, we’re interested in hearing from you.
US, WA, Seattle
MULTIPLE POSITIONS AVAILABLE Employer: AMAZON.COM SERVICES LLC Offered Position: Research Scientist II Job Location: Seattle, Washington Job Number: AMZ10564041 Position Responsibilities: Interact with various software and business groups to develop an understanding of their business requirements and operational processes. Utilize acquired knowledge and business judgment to build decision-supporting and operational tools to improve the bottom line. Build quantitative mathematical models to represent a wide range of supply chain, transportation and logistics systems. Implement these models and tools through the use of modeling languages and engineering code in software languages such as Java, C++, C# or C. Gather required data for analysis and mathematical model building by writing ad-hoc scripts and database queries. Perform quantitative, economic, and numerical performance analyses of these systems under uncertainty using statistical and optimization tools. Create computer simulations to support operational decision-making. Identify areas with potential for improvement and work with internal teams to generate requirements to realize improvements. Design optimal or near optimal solution methodologies to be used by in-house decision support tools and software. Create software prototypes to verify and validate the devised solutions methodologies. Integrate prototypes into production systems using standard software development tools and methodologies. 40 hours / week, 8:00am-5:00pm, Salary Range: $136,000/year to $184,000/year Amazon is a total compensation company. Dependent on the position offered, equity, sign-on payments, and other forms of compensation may be provided as part of a total compensation package, in addition to a full range of medical, financial, and/or other benefits. For more information, visit: https://www.aboutamazon.com/workplace/employee-benefits. Amazon.com is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation.#0000
US, NY, New York
MULTIPLE POSITIONS AVAILABLE Employer: AMAZON.COM SERVICES LLC Offered Position: Applied Scientist II Job Location: New York, New York Job Number: AMZ10564066 Position Responsibilities: Participate in the design, development, evaluation, deployment and updating of data-driven models and analytical solutions for machine learning (ML) and/or natural language (NL) applications. Develop and/or apply statistical modeling techniques (e.g. Bayesian models and deep neural networks), optimization methods, and other ML techniques to different applications in business and engineering. Routinely build and deploy ML models on available data. Research and implement novel ML and statistical approaches to add value to the business. Mentor junior engineers and scientists. 40 hours / week, 8:00am-5:00pm, Salary Range: $172,400/year to $223,400/year. Amazon is a total compensation company. Dependent on the position offered, equity, sign-on payments, and other forms of compensation may be provided as part of a total compensation package, in addition to a full range of medical, financial, and/or other benefits. For more information, visit: https://www.aboutamazon.com/workplace/employee-benefits. Amazon.com is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation.#0000
US, TX, Austin
MULTIPLE POSITIONS AVAILABLE Employer: AMAZON.COM SERVICES LLC Offered Position: Data Scientist III Job Location: Austin, Texas Job Number: AMZ10593703 Position Responsibilities: Own the data science elements of various products to help with data-based decision making, product performance optimization, and product performance tracking. Work directly with product managers to help drive the design of the product. Work with Technical Product Managers to help drive the build planning. Translate business problems and products into data requirements and metrics. Initiate the design, development, and implementation of scientific analysis projects or deliverables. Own the analysis, modelling, system design, and development of data science solutions for products. Write documents and make presentations that explain model/analysis results to the business. Bridge the degree of uncertainty in both problem definition and data scientific solution approaches. Build consensus on data, metrics, and analysis to drive business and system strategy. Position Requirements: Master's degree or foreign equivalent degree in Statistics, Applied Mathematics, Economics, Engineering, Computer Science or a related field and two years of experience in the job offered or a related occupation. Employer will accept a Bachelor's degree or foreign equivalent degree in Statistics, Applied Mathematics, Economics, Engineering, Computer Science, or a related field and five years of progressive post-baccalaureate experience in the job offered or a related occupation as equivalent to the Master's degree and two years of experience. Must have one year of experience in the following skills: (1) building statistical models and machine learning models using large datasets from multiple resources; (2) building complex data analyses by leveraging scripting languages including Python, Java, or related scripting language; and (3) communicating with users, technical teams, and management to collect requirements, evaluate alternatives, and develop processes and tools to support the organization. Amazon.com is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation. 40 hours / week, 8:00am-5:00pm, Salary Range $159,200/year to $215,300/year. Amazon is a total compensation company. Dependent on the position offered, equity, sign-on payments, and other forms of compensation may be provided as part of a total compensation package, in addition to a full range of medical, financial, and/or other benefits. For more information, visit: https://www.aboutamazon.com/workplace/employee-benefits. #0000
US, WA, Seattle
Amazon Ads is one of the fastest-growing advertising businesses in the world, connecting brands with hundreds of millions of customers across shopping, streaming, gaming, audio and the open web. Behind every ad that runs on Prime Video, Twitch, IMDb and thousands of external publisher apps and sites is a decisioning platform built by Amazon Ads Supply Tech. That platform makes X trillion ad decisions every day and supports $XB+ in annual publisher revenue across XX+ Amazon-owned publishers and X,000+ external publishers in streaming TV, audio, display, mobile and podcasts. Every one of those decisions is a science problem: which inventory qualifies for which buyers, how publisher commitments are paced and delivered, which ad wins among competing candidates, and what price maximizes long-term yield. Each must be solved in milliseconds, under strict latency and cost budgets, while balancing advertisers, publishers, viewers and Amazon. At this scale, a fraction-of-a-percent model improvement is worth $X millions. We are looking for a Principal Applied Scientist to set the science strategy for this platform. You will decide where machine learning creates the most value, bring intelligence into real-time runtime systems, and lead models from idea to production. Your work will directly shape three of Amazon Ads’ biggest priorities: growing Amazon-owned and third-party supply, enabling full-funnel advertising, and building agentic, AI-driven workflows for publishers and advertisers. As a principal, you will be a technical leader across the organization. You will raise the science bar, mentor senior scientists, and influence product and engineering leaders. You will work alongside excellent, driven scientists, engineers and product leaders who take on hard problems and invest in each other’s growth. Few places in the world operate at this scale. Key job responsibilities - Define the ML strategy for the ad decisioning platform. Set a multi-year science vision across pricing, yield optimization, forecasting, ad selection and commitment delivery, tied to measurable business outcomes. - Identify opportunities to deploy intelligence in runtime systems. Find where rules and heuristics in real-time serving paths can be replaced or improved by learned models, and partner with engineering to fit them within latency, compute and reliability budgets. - Build ML models that operate at X trillion decisions a day, drawing on approaches such as deep learning, reinforcement learning and bandits, causal inference, forecasting, and auction and mechanism design. - Evaluate ML models rigorously. Design offline, counterfactual and off-policy evaluations and online experiments. Define metrics that capture long-term value for advertisers, publishers and viewers, not just short-term lift. - Refine models for output quality and performance. Improve accuracy, calibration and robustness, cut serving latency and cost, and monitor models in production for drift and degradation. - Lead science across the organization. Set technical standards, review science designs and launches, and mentor and grow senior and principal-track scientists. - Push the frontier, including LLM and agentic approaches, and contribute to Amazon’s internal and external science community through papers, talks and patents. A day in the life Start the day reviewing off-policy evaluation results for a new pricing model that projects an X% yield lift, and deciding with your team whether it is ready for an online test. Next, you work with engineers on fitting a deeper model into a millisecond latency budget at X billion requests. At midday, you dig into why a forecasting model drifted during a live sports event, and sketch a fix. Later, you review a scientist’s paper draft and present the science roadmap to product leaders. Throughout, you work with brilliant, driven colleagues who sharpen your thinking and help you grow. About the team Ads Decisioning team brings together applied scientists and product managers to build the intelligence behind Amazon’s publisher business. We serve Amazon-owned publishers such as Prime Video, Twitch and IMDb, along with thousands of external publishers across streaming TV, audio and display. Our models decide, in milliseconds, which inventory qualifies for which buyers, how commitments are delivered, which ad wins and at what price, balancing advertisers, publishers, viewers and Amazon. We pair scientific rigor with a bias for production impact, learn from each other, and invest in each other’s growth. Come solve problems few teams anywhere get to work on.