Physics-constrained machine learning for scientific computing

Amazon researchers draw inspiration from finite-volume methods and adapt neural operators to enforce conservation laws and boundary conditions in deep-learning models of physical systems.

Commercial applications of deep learning have been making headlines for years — never more so than this spring. More surprisingly, deep-learning methods have also shown promise for scientific computing, where they can be used to predict solutions to partial differential equations (PDEs). These equations are often prohibitively expensive to solve numerically; using data-driven methods has the potential to transform both scientific and engineering applications of scientific computing, including aerodynamics, ocean and climate, and reservoir modeling.

A fundamental challenge is that the predictions of deep-learning models trained on physical data typically ignore fundamental physical principles. Such models might, for instance, violate system conservation laws: the solution to a heat transfer problem may fail to conserve energy, or the solution to a fluid flow problem may fail to conserve mass. Similarly, a model’s solution may violate boundary conditions — say, allowing heat flow through an insulator at the boundary of a physical system. This can happen even when the model’s training data includes no such violations: at inference time, the model may simply extrapolate from patterns in the training data in an illicit way.

In a pair of recent papers accepted at the International Conference on Machine Learning (ICML) and the International Conference on Learning Representations (ICLR), we investigate the problems of adding known physics constraints to the predictive outputs of machine learning (ML) models when computing the solutions to PDEs.

Related content
Danielle Maddix Robinson's mathematics background helps inform robust models that can predict everything from retail demand to epidemiology.

The ICML paper, “Learning physical models that can respect conservation laws”, which we will present in July, focuses on satisfying conservation laws with black-box models. We show that, for certain types of challenging PDE problems with propagating discontinuities, known as shocks, our approach to constraining model outputs works better than its predecessors: it more sharply and accurately captures the physical solution and its uncertainty and yields better performance on downstream tasks.

In this paper, we collaborated with Derek Hansen, a PhD student in the Department of Statistics at the University of Michigan, who was an intern at AWS AI Labs at the time, and Michael Mahoney, an Amazon Scholar in Amazon’s Supply Chain Optimization Technologies organization and a professor of statistics at the University of California, Berkeley.

In a complementary paper we presented at this year’s ICLR, “Guiding continuous operator learning through physics-based boundary constraints”, we, together with Nadim Saad, an AWS AI Labs intern at the time and a PhD student at the Institute for Computational and Mathematical Engineering (ICME) at Stanford University, focus on enforcing physics through boundary conditions. The modeling approach we describe in this paper is a so-called constrained neural operator, and it exhibits up to a 20-fold performance improvement over previous operator models.

So that scientists working with models of physical systems can benefit from our work, we’ve released the code for the models described in both papers (conservation laws | boundary constraints) on GitHub. We also presented on both works in March 2023 at AAAI's symposium on Computational Approaches to Scientific Discovery.

Danielle Maddix Robinson on physics-constrained machine learning for scientific computing
A talk presented in April 2023 at the Machine Learning and Dynamical Systems Seminar at the Alan Turing Institute.

Conservation laws

Recent work in scientific machine learning (SciML) has focused on incorporating physical constraints into the learning process as part of the loss function. In other words, the physical information is treated as a soft constraint or regularization.

Related content
Hybrid model that combines machine learning with differential equations outperforms models that use either strategy by itself.

A main issue with these approaches is that they do not guarantee that the physical property of conservation is satisfied. To address this issue, in “Learning physical models that can respect conservation laws”, we propose ProbConserv, a framework for incorporating constraints into a generic SciML architecture. Instead of expressing conservation laws in the differential forms of PDEs, which are commonly used in SciML as extra terms in the loss function, ProbConserv converts them into their integral form. This allows us to use ideas from finite-volume methods to enforce conservation.

In finite-volume methods, a spatial domain — say, the region through which heat is propagating — is discretized into a finite set of smaller volumes called control volumes. The method maintains the balance of mass, energy, and momentum throughout this domain by applying the integral form of the conservation law locally across each control volume. Local conservation requires that the out-flux from one volume equals the in-flux to an adjacent volume. By enforcing the conservation law across each control volume, the finite-volume method guarantees global conservation across the whole domain, where the rate of change of the system’s total mass is given by the change in fluxes along the domain boundaries.

Flux Volume Edit-01_230525135151.jpg
The integral form of a conservation law states that the rate of change of the total mass of the system over a domain (Ω) is equal to the difference between the in-flux and out-flux along the domain boundaries (∂Ω).

More specifically, the first step in the ProbConserv method is to use a probabilistic machine learning model — such as a Gaussian process, attentive neural process (ANP), or ensembles of neural-network models — to estimate the mean and variance of the outputs of the physical model. We then use the integral form of the conservation law to perform a Bayesian update to the mean and covariance of the distribution of the solution profile such that it satisfies the conservation constraint exactly in the limit.

Related content
Learning the complete quantile function, which maps probabilities to variable values, rather than building separate models for each quantile level, enables better optimization of resource trade-offs.

In the paper, we provide a detailed analysis of ProbConserv’s application to the generalized porous-medium equation (GPME), a widely used parameterized family of PDEs. The GPME has been used in applications ranging from underground flow transport to nonlinear heat transfer to water desalination and beyond. By varying the PDE parameters, we can describe PDE problems with different levels of complexity, ranging from “easy” problems, such as parabolic PDEs that model smooth diffusion processes, to “hard” nonlinear hyperbolic-like PDEs with shocks, such as the Stefan problem, which has been used to model two-phase flow between water and ice, crystal growth, and more complex porous media such as foams.

For easy GPME variants, ProbConserv compares well to state-of-the-art competitors, and for harder GPME variants, it outperforms other ML-based approaches that do not guarantee volume conservation. ProbConserv seamlessly enforces physical conservation constraints, maintains probabilistic uncertainty quantification (UQ), and deals well with the problem of estimating shock propagation, which is difficult given ML models’ bias toward smooth and continuous behavior. It also effectively handles heteroskedasticity, or fluctuation in variables’ standard deviations. In all cases, it achieves superior predictive performance on downstream tasks, such as predicting shock location, which is a challenging problem even for advanced numerical solvers.

Examples

Conservation of mass.png
Conservation of mass can be violated by a black-box deep-learning model (here, the ANP), even when the PDE is applied as a soft constraint (here, SoftC-ANP) on the loss function, à la physics-informed neural networks (PINNs). This figure shows the variation of total mass over time for the smooth constant coefficient diffusion equation (an “easy” GPME example). The true mass remains zero, since there is zero net flux from the domain boundaries, and thus mass cannot be created or destroyed in the domain interior.
Uncertainty quantification.png
Density solution profiles with uncertainty quantification. In the “hard” version of the GPME problem, also known as the Stefan problem, the solution profile may contain a moving sharp interface in space, known as a shock. The shock here separates the region with fluid from the degenerate one with zero fluid density. The uncertainty is largest in the shock region and becomes smaller in the areas away from it. The main idea behind ProbConserv’s UQ method is to use the uncertainty in the unconstrained black box to modify the mean and covariance at the locations where the variance is largest, to satisfy the conservation constraint. The constant-variance assumption in the HardC-ANP baseline does not result in improvement on this hard task, while ProbConserv results in a better estimate of the solution at the shock and a threefold improvement in the mean squared error (MSE).
Shock position.png
Downstream task. Histogram of the posterior of the shock position computed by ProbConserv and the other baselines. While the baseline models skew the distribution of the shock position, ProbConserv computes a distribution that is well-centered around the true shock position. This illustrates that enforcing physical constraints such as conservation is necessary in order to provide reliable and accurate estimations of the shock position.

Boundary conditions

Boundary conditions (BCs) are physics-enforced constraints that solutions of PDEs must satisfy at specific spatial locations. These constraints carry important physical meaning and guarantee the existence and the uniqueness of PDE solutions. Current deep-learning-based approaches that aim to solve PDEs rely heavily on training data to help models learn BCs implicitly. There is no guarantee, though, that these models will satisfy the BCs during evaluation. In our ICLR 2023 paper, “Guiding continuous operator learning through physics-based boundary constraints”, we propose an efficient, hard-constrained, neural-operator-based approach to enforcing BCs.

Related content
Amazon quantum computing scientist recognized for ‘outstanding contributions to physics’.

Where most SciML methods (for example, PINNs) parameterize the solution to PDEs with a neural network, neural operators aim to learn the mapping from PDE coefficients or initial conditions to solutions. At the core of every neural operator is a kernel function, formulated as an integral operator, that describes the evolution of a physical system over time. For our study, we chose the Fourier neural operator (FNO) as an example of a kernel-based neural operator.

We propose a model we call the boundary-enforcing operator network (BOON). Given a neural operator representing a PDE solution, a training dataset, and prescribed BCs, BOON applies structural corrections to the neural operator to ensure that the predicted solution satisfies the system BCs.

BOON architecture full.png
BOON architectures. Kernel correction architectures for commonly used Dirichlet, Neumann, and periodic boundary conditions that carry different physical meanings.

We provide our refinement procedure and demonstrate that BOON’s solutions satisfy physics-based BCs, such as Dirichlet, Neumann, and periodic. We also report extensive numerical experiments on a wide range of problems including the heat and wave equations and Burgers's equation, along with the challenging 2-D incompressible Navier-Stokes equations, which are used in climate and ocean modeling. We show that enforcing these physical constraints results in zero boundary error and improves the accuracy of solutions on the interior of the domain. BOON’s correction method exhibits a 2-fold to 20-fold improvement over a given neural-operator model in relative L2 error.

Examples

Insulator at boundary.png
Nonzero flux at an insulator on the boundary. The solution to the unconstrained Fourier-neural-operator (FNO) model for the heat equation has a nonzero flux at the left insulating boundary, which means that it allows heat to flow through an insulator. This is in direct contradiction to the physics-enforced boundary constraint. BOON, which satisfies this so-called Neumann boundary condition, ensures that the gradient is zero at the insulator. Similarly, at the right boundary, we see that the FNO solution has a negative gradient at a positive heat source and that the BOON solution corrects this nonphysical result. Guaranteeing no violation of the underlying physics is critical to the practical adoption of these deep-learning models by practitioners in the field.
Stokes's second problem.png
Stokes’s second problem. This figure shows the velocity profile and corresponding absolute errors over time obtained by BOON (top). BOON improves the accuracy at the boundary, which, importantly, also improves accuracy on the interior of the domain compared to the unconstrained Fourier-neural-operator (FNO) model (bottom), where the errors at the boundary propagate inward over time.
Initial condition.png
2-D Navier-Stokes lid-driven cavity flow initial condition. The initial vorticity field (perpendicular to the screen), which is defined as the curl of the velocity field. At the initial time step, t = 0, the only nonzero component of the horizontal velocity is given by the top constant Dirichlet boundary condition, which drives the viscous incompressible flow at the later time steps. The other boundaries have the common no-slip Dirichlet boundary condition, which fixes the velocity to be zero at those locations.

Navier-Stokes lid-driven flow
2-D Navier-Stokes lid-driven cavity flow vorticity field. The vorticity field (perpendicular to the screen) within a square cavity filled with an incompressible fluid, which is induced by a fixed nonzero horizontal velocity prescribed by the Dirichlet boundary condition at the top boundary line for a 25-step (T=25) prediction until final time t = 2.
2-D Navier-Stokes lid-driven cavity flow relative error.
The L2 relative-error plots show significantly higher relative error over time for the data-driven Fourier neural operator (FNO) compared to that of our constrained BOON model on the Navier-Stokes lid-driven cavity flow problem for both a random test sample and the average over the test samples.

Acknowledgements: This work would have not been possible without the help of our coauthor Michael W. Mahoney, an Amazon Scholar; coauthors and PhD student interns Derek Hansen and Nadim Saad; and mentors Yuyang Wang and Margot Gerritsen.

Research areas

Related content

US, CA, Pasadena
The Amazon Web Services (AWS) Center for Quantum Computing (CQC) in Pasadena, CA, is hiring an Applied Scientist to lead integration research and development for superconducting quantum devices. You will design, model, and test the chip-to-chip, chip-to-package, and signal-delivery interfaces that let superconducting quantum computers scale, and you will characterize integrated assemblies at cryogenic temperatures to learn how integration choices affect qubit performance, yield, and manufacturability. You will join a multi-disciplinary team of theoretical and experimental physicists, materials scientists, and hardware and software engineers working at the forefront of quantum computing. You will carry integration technologies from concept through hardware demonstration, build the test standards and automation that make results reproducible across devices, and collaborate with fabrication, hardware, and circuit design engineers to remove the dominant sources of yield loss. You will also contribute to multi-year roadmap planning for integration and scaling capabilities and help establish the scientific foundation for this capability area within the Device team. Key job responsibilities In this role you will develop the integration technologies that let superconducting quantum computers scale. Your work will span four connected areas: - Integration research and development: Design, model, and test integration solutions for superconducting quantum devices, including chip-to-chip, chip-to-package, and signal-delivery interfaces. Build electromagnetic, thermal, and mechanical models to predict and optimize performance, and characterize integrated assemblies at cryogenic temperatures. - Scaling technologies: Develop and evaluate approaches to scaling superconducting quantum hardware against yield, reusability, manufacturability, and scalability, and carry the most promising ones from concept through hardware demonstration. - Test standards and automation: Define test standards that give rigorous, reproducible measurements of how integration affects qubit coherence, loss, and crosstalk. Automate data collection and reporting against these standards so characterization scales across devices and configurations. - Yield and manufacturability: Work with fabrication, hardware, printed circuit board, and circuit design engineers to identify and remove the largest sources of yield loss and integration uncertainty, and to design processes and components that are reused across device generations and manufactured at scale. About the team The Device team at the AWS Center for Quantum Computing designs, builds, and measures the superconducting quantum devices at the heart of our processors, and develops the integration and packaging that turn individual devices into working systems. You will work alongside physicists, materials scientists, and hardware and software engineers across design, fabrication, measurement, and theory, in a lab built for rapid iteration from concept to cryogenic test. Over the coming years the team's focus is making superconducting quantum hardware scale, and this role establishes integration as a scientific capability area within that effort. Why AWS? Amazon Web Services (AWS) is the world's most comprehensive and broadly adopted cloud platform. We pioneered cloud computing and never stopped innovating — that's why customers from the most successful startups to Global 500 companies trust our robust suite of products and services to power their businesses. AWS Utility Computing (UC) provides product innovations — from foundational services such as Amazon's Simple Storage Service (S3) and Amazon Elastic Compute Cloud (EC2), to consistently released new product innovations that continue to set AWS's services and features apart in the industry. As a member of the UC organization, you'll support the development and management of Compute, Database, Storage, Internet of Things (IoT), Platform, and Productivity Apps services in AWS. Within AWS UC, Amazon Dedicated Cloud (ADC) roles engage with AWS customers who require specialized security solutions for their cloud services. Inclusive Team Culture: Here at AWS, it's in our nature to learn and be curious. Our employee-led affinity groups foster a culture of inclusion that empower us to be proud of our differences. Ongoing events and learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (diversity) conferences, inspire us to never stop embracing our uniqueness. Diverse Experiences: AWS values diverse experiences. Even if you do not meet all of the preferred qualifications and skills listed in the job description, we encourage candidates to apply. If your career is just starting, hasn't followed a traditional path, or includes alternative experiences, don't let it stop you from applying. Mentorship & Career Growth: We're continuously raising our performance bar as we strive to become Earth's Best Employer. That's why you'll find endless knowledge-sharing, mentorship and other career-advancing resources here to help you develop into a better-rounded professional. Work/Life Balance: We value work-life harmony. Achieving success at work should never come at the expense of sacrifices at home, which is why we strive for flexibility as part of our working culture. When we feel supported in the workplace and at home, there's nothing we can't achieve in the cloud.
US, VA, Arlington
PXT Central Science is seeking an exceptional Data Scientist to join our team. The ideal candidate will thrive in a dynamic, multifaceted role where you'll translate complex business challenges into rigorous quantitative frameworks, extract actionable insights from structured and unstructured datasets, and architect science-backed, scalable solutions that elevate the experience of our 1 million+ employees worldwide. If you're energized by the opportunity to apply data science to our mission of making Amazon Earth's Best Employer, we want to hear from you. Key job responsibilities • Own the design, development, and maintenance of scalable models and prototypes leveraging statistical, machine learning, or GenAI methodologies to enhance employee experience. • Partner with scientists, engineers, and product leaders to solve for employee experience defects using scientific approaches, building new services and tools that deliverable measurable impact. • Author and maintain detailed technical documentation related to the projects you drive. • Communicate results to diverse audiences of varying technical background with effective writing, visualizations, and presentations • Stay current with emerging methods and technologies, and implement them strategically to amplify the team’s impact. About the team The Central Science Team within Amazon’s People Experience and Technology org (PXTCS) uses economics, behavioral science, statistics, machine learning, and Generative AI to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, well-being, and the value of work to Amazonians. We are an interdisciplinary team, which combines the talents of science, engineering, and UX to develop and deliver solutions that measurably achieve this goal.
CA, BC, Vancouver
Building AI first solutions in a complex regulated space at Amazon scale. Would you like to work on one of the world's largest product classification and Tax computation engine? Or perhaps teaching AI to understanding nuances of domain specific language is what piques your interest? We are responsible for the tax calculation platform, providing the core services that calculate indirect taxes (sales tax and VAT) for all Amazon sales, physical and digital, globally. We are responsible for classifying billions of products in Amazon’s catalogue, calculating accurate Tax amount for every transaction that happens on Amazon’s global platform. Our engineering services are relied upon globally, built to be resilient across some of highest peak traffic demands in the world, while constantly evolving with the state of the art technology. We use language models at scale for Tax classification of the diverse products in Amazon catalogue and comprehending nuances of legislations and legal parlour.Our challenges include staying on top of the complex and fast-changing global tax legislations while ensuring computing calculations correctly and quickly, thousands of times a second, and each one needs to be accurate. Applied Scientists in Tax Engine works closely with Tax specialists, Product team , SDEs and Business teams - tackling a growing portfolio of core-science problems that includes balance of predictive and generative AI -including language comprehension, causal reasoning and active learning. As an Applied scientist, you will provide machine learning expertise to the team that helps increase the accuracy of Tax classification based on product information in Amazon catalogue. You will build various machine learning models to predict accuracy of tax classification, work with large reasoning models to reason with large volumes of system data and expert artefacts to teach domain intuition to AI. You will on variety of legislative changes acting as causal determinants to changes in our systems. You will help us innovate different ways to enhance for our global customers of Amazon.You will need to be entrepreneurial, work in a highly collaborative environment with SDEs, Product managers and businesses. We like to move fast, experiment, iterate and then scale quickly, thoughtfully balancing speed and quality. Whether you're passionate about taking your scientific solves to global reach and scale or one who seeks to solve complex problems under high scrutiny of an audited field, Tax Engine’s scope could offer you an intersting challenge to solve.
US, NY, New York
Prime Video is a first-stop entertainment destination offering customers a vast collection of premium programming in one app available across thousands of devices. Prime members can customize their viewing experience and find their favorite movies, series, documentaries, and live sports – including Amazon MGM Studios-produced series and movies; licensed fan favorites; and programming from Prime Video subscriptions such as Apple TV+, HBO Max, Peacock, Crunchyroll and MGM+. All customers, regardless of whether they have a Prime membership or not, can rent or buy titles via the Prime Video Store, and can enjoy even more content for free with ads. Are you interested in shaping the future of entertainment? Prime Video's technology teams are creating best-in-class digital video experience. As a Prime Video team member, you’ll have end-to-end ownership of the product, user experience, design, and technology required to deliver state-of-the-art experiences for our customers. You’ll get to work on projects that are fast-paced, challenging, and varied. You’ll also be able to experiment with new possibilities, take risks, and collaborate with remarkable people. We’ll look for you to bring your diverse perspectives, ideas, and skill-sets to make Prime Video even better for our customers. With global opportunities for talented technologists, you can decide where a career Prime Video Tech takes you! Key job responsibilities The science challenges include: - Heterogeneous customer responses. The same customer responds differently to ads depending on what they’re watching, how engaged they are, and their broader streaming context. We need to understand and predict this variation to make better advertising decisions in real time. - Signal sparsity in streaming. Unlike search or retail advertising, streaming offers no clicks, no conversions, and limited direct feedback. We must develop creative approaches to infer customer preferences, intent, and tolerance from indirect behavioral signals. - Personalization at scale. A one-size-fits-all ad experience leaves value on the table for both customers and the business. We build systems that adapt ad load, placement, and content to individual viewers across 100M+ customers and 100k+ titles. - Small effects, large variance. Ad interventions typically produce 0.1-2% shifts in engagement, effects easily overwhelmed by natural behavioral variance. Measuring, attributing, and optimizing these small signals requires rigorous experimental design and causal methodologies. - Competing objectives. Revenue, customer engagement, long-term retention, and advertiser value are in tension. We develop principled frameworks to navigate these tradeoffs and optimize for sustainable outcomes rather than any single metric. A day in the life - Lead the research and development of ML models that personalize advertising decisions for 100M+ customers across 100k+ titles, with production deployment in mind - Develop deep learning architectures (multi-task learning, embedding-based representations) for customer behavior prediction at scale - Design and analyze large-scale A/B experiments, applying causal inference techniques to measure and optimize the impact of ad strategies on customer engagement and monetization - Partner with engineering to ensure models meet production latency and scalability requirements - Collaborate with product managers to frame business problems as tractable ML problems and translate findings into product decisions - Shape the team’s scientific roadmap, identifying high-impact research directions About the team Prime Video Ads is pioneering the use of Generative AI, Deep Learning and Causal ML to empower the next generation of Ads experience in Prime Video. Our vision is to build the world’s most valuable and differentiated ad-supported streaming platform: one where every ad is relevant to the viewer, and every dollar spent by an advertiser delivers measurable results. We are seeking lead applied scientists who have demonstrated experience in advancing state of the art ML algorithms, particularly in Personalization, Relevance, Casual Inference and Gen-AI areas. Your role will be to deliver these innovations as production-ready systems at Amazon scale.
US, WA, Seattle
MULTIPLE POSITIONS AVAILABLE Employer: AMAZON.COM SERVICES LLC Offered Position: Applied Scientist II Job Location: Seattle, Washington Job Number: AMZ10564086 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. Specialize in the field of Computational Advertising, directly advancing the techniques in Online Advertising Technology focusing on model optimization and latency reduction. Develop sophisticated machine learning algorithms and models using PyTorch. Develop advanced deep learning architectures to automate the discovery of complex, non-linear feature interactions, effectively capturing high-dimensional data patterns that traditional statistical models are unable to process. Investigate and implement high-order feature interaction architectures, such as DeepFM and DCN-V2, using PyTorch to capture complex non-linear relationships within sparse categorical datasets. Develop custom embedding layers in PyTorch to map high-dimensional, sparse features (e.g., Ad IDs) into dense, low-dimensional vector spaces. Conduct systematic research into the trade-offs between model architecture complexity and inference speed, utilizing PyTorch profiling tools to identify and optimize bottleneck layers. 40 hours / week, 8:00am-5:00pm, Salary Range: $163,617/year to $193,200/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, WA, Redmond
Amazon Leo is Amazon’s low Earth orbit satellite constellation initiative designed to bring fast, affordable broadband connectivity to unserved and underserved communities around the world. We are building a next-generation satellite system from the ground up — designing everything from the spacecraft and payload to the ground infrastructure and customer terminals. This is a rare opportunity to join a team that is shaping the future of global connectivity at scale. The Leo Antenna team is looking for an RF Systems Scientist who is excited to work at the intersection of radio frequency engineering, phased array antennas, large-scale data analysis, and hardware reliability. You will turn data from our customer terminal fleet into engineering decisions. Every terminal in the field reports a steady stream of telemetry: downlink and uplink signal quality, link state, antenna pointing, temperature, and reboots. Every terminal was also tested in the factory before it shipped, and the network sees every contact it makes with a satellite. Your job is to connect these sources. You'll find out which field behaviors trace back to the antenna hardware and which come from the installation, the sky around the terminal, the network, or a software release. You'll also look for patterns that point to weaknesses in the design. Your findings will shape how we design, build, test, and support the next generation of customer terminals. A typical problem starts small. A few terminals spend far more time recovering their link than their neighbors, run a little hotter than the rest of the fleet, or reboot more often than they should. You'll work out whether it's a real effect or noise, whether it's spreading, and what the affected terminals have in common. They might share a hardware revision, a software version, a location, or a signature in their factory test history. From there you'll form a hypothesis about the physical cause and argue it in front of antenna, RF, and software engineers who will push back hard. You'll also have to say plainly when the data rules your own idea out. To find the cause, you'll pull in the rest of each terminal's history: its factory and thermal test results, its software and reboot record, and what the satellite measured on the other side of the link. Some questions can be answered from data we already collect. For the rest, you'll decide what new measurement or test would answer them, work with the teams who can run it, and report what the results show and what should happen next. Beyond individual investigations, you'll build the fleet-level view. That means expected performance for a healthy terminal given where it is and what it sees, early warning signals for hardware that is starting to fail, and measures of how software releases and hardware revisions change the fleet. You'll decide which recurring analyses should become automated monitoring and work with software engineers to build them into our fleet health system. You'll be the person the team turns to when someone asks "is this terminal normal?" The ideal candidate understands how radio links and phased array antennas behave, is curious about how hardware fails, and is comfortable with messy data from many sources. They can turn "a few terminals look odd" into a rigorous analysis and a clear recommendation. 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 Analyze customer terminal telemetry to measure antenna and link performance in the field, and detect failing hardware and slow degradation early Investigate underperforming terminals and field service requests, separating hardware effects from installation, obstruction, network, and software effects, and decide what should happen next Connect events across the fleet by hardware revision, manufacturing lot, software version, and location, and measure the effect of software releases and hardware changes on the fleet Correlate field behavior with factory and thermal test results, and feed what you learn back into test limits, screening, and the design of the next generation of terminals Define the fleet health metrics and baselines, specify the telemetry they need, and work with software engineers to turn recurring analyses into automated monitoring Build dashboards and AI-assisted tools that support fleet health reviews, field investigations, and design reviews Lead investigations that span several teams, from the first hypothesis to a decision, and present the evidence and recommendation to senior engineering leaders About the team The Leo Antenna team designs the phased array antenna inside Leo's customer terminals. It is the electronically steered panel that tracks satellites across the sky and carries every customer's connection. We own the antenna from simulation and design through factory test automation and thermal testing, and we own how it performs once it's installed at a customer's site. That includes the telemetry analysis and the fleet health system that keeps a daily hardware health record for every terminal in the field. We are a hardware-facing team that writes a lot of software, and we sit where several disciplines meet: antenna and RF design, terminal software, manufacturing, network operations, and field service. Every terminal has a part-level history, from its factory test results to every satellite contact it makes in the field. A large part of our work is investigation. When a terminal underperforms, we work out whether the cause is the hardware, the installation, the sky around it, the network, or the software, and we decide what should happen next. We have built analyses that map each terminal's view of the sky from its pointing and signal data, dashboards the wider organization uses every day, and AI-assisted tools that let engineers query telemetry and turn raw data into conclusions. We care about evidence over assumption. A ticket that lists a terminal doesn't explain it, and an obstruction request isn't an obstruction until the data shows one. Theories get tested against the data before they're accepted. Because we own both ends, from the first factory test to performance in the field, the loop is closed within the team. What we learn from the fleet goes straight back into our designs and test screens, so the next terminal we ship is more likely to work well for the customer who receives it.
US, WA, Seattle
Here at Amazon, we embrace our differences. We are committed to furthering our culture of diversity and inclusion of our teams within the organization. How do you get items to customers quickly, cost-effectively, and—most importantly—safely, in less than an hour? And how do you do it in a way that can scale? Our teams of hundreds of scientists, engineers, aerospace professionals, and futurists have been working hard to do just that! We are delivering to customers, and are excited for what’s to come. Check out more information about Prime Air on the About Amazon blog (https://www.aboutamazon.com/news/transportation/amazon-prime-air-delivery-drone-reveal-photos). If you are seeking an iterative environment where you can drive innovation, apply state-of-the-art technologies to solve real world delivery challenges, and provide benefits to customers, Prime Air is the place for you. Come work on the Amazon Prime Air Team! Prime Air's Flight Sciences High-Fidelity Methods (HFM) team is seeking an outstanding Applied Scientist to develop and verify drone systems models and flight physics models. These models form the backbone of every flight simulation performed within Prime Air, directly informing aircraft design, system verification, certification, and business decisions. The HFM team's work enables prediction of critical vehicle performance metrics—including range, maneuverability, tracking error, and aircraft stability—and connects vehicle design and operational decisions to business outcomes such as customer reachability. Our models are also a crucial input to the design of flight control algorithms and software verification. Because the accuracy and reliability of these models underpin so many facets of Prime Air's mission, the scientist in this role will have broad, high-visibility impact on the program's success. Key job responsibilities The Applied Scientist in this role will own the end-to-end lifecycle of simulation models—from development and deployment through verification and ongoing maintenance. This begins with gathering downstream customer needs, selecting the most suitable modeling approach and level of fidelity, and coordinating the generation of input data. It extends through model training, development and maintenance of software interfaces, and verification of model accuracy. A core aspect of this role is determining the right modeling approach for a given physical phenomenon. The scientist will need a working understanding of the physics and systems being modeled, including vehicle aerodynamics, propeller performance, multibody dynamics, atmospheric physics, electric powertrain components, and guidance and navigation system (GNS) sensors. They will design experiments to generate the data needed to build and verify models, and apply uncertainty quantification and statistical analyses to validate model fidelity.
US, CA, Palo Alto
Amazon Ads helps advertisers reach customers across Amazon's stores, Prime Video, Fire TV, Alexa, Twitch, and the open internet. Every ad we serve has to be safe, compliant, and trustworthy. The Ads Trust science team builds the AI systems that does this by reviewing billions of ads across text, image, video, audio, and product listings. We are looking for a Principal Applied Scientist to set the science direction for this work. This is an opportunity to apply as well as build state-of-the-art AI to problems where accuracy, scale, and customer trust all matter at once. This role suits a scientist who wants to own a hard problem end to end: inventing methods, proving them with strong evaluation, and putting them in front of customers. You will design the core modeling approach behind moderation at Amazon scale. That includes multimodal large language and vision-language models, retrieval-based labeling, model distillation for production, and customer facing agentic systems. You will take ambiguous, high-stakes problems, turn them into scientific roadmaps, and stay hands-on in the technical decisions that matter most. You will set the bar for scientific rigor, evaluation, and design reviews across a multi-team organization. You will also mentor senior scientists and partner with engineering, product, and policy leaders to get research into production. Key job responsibilities - Set the multi-year science strategy for automated content moderation, with high accuracy and efficiency as the goals. - Lead the design of multimodal and multilingual models for labeling and policy classification across text, image, video, audio, and product assets. - Drive methods that turn frontier-model quality into cost-efficient production systems, such as distillation, retrieval-augmented labeling, and efficient inference. - Define evaluation standards and measurement frameworks that set the quality bar for production models. - Own science low-level design reviews across teams and raise the technical bar for modeling, experimentation, and launch readiness. - Mentor and develop senior and mid-level scientists, and grow scientific leadership across the organization. - Influence engineering, product, and policy partners, and represent Amazon Ads science through publications and external collaborations.
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.