Computing on private data

Both secure multiparty computation and differential privacy protect the privacy of data used in computation, but each has advantages in different contexts.

Many of today’s most innovative computation-based products and solutions are fueled by data. Where those data are private, it is essential to protect them and to prevent the release of information about data subjects, owners, or users to the wrong parties. How can we perform useful computations on sensitive data while preserving privacy?

Related content
Technique that mixes public and private training data can meet differential-privacy criteria while cutting error increase by 60%-70%.

We will revisit two well-studied approaches to this challenge: secure multiparty computation (MPC) and differential privacy (DP). MPC and DP were invented to address different real-world problems and to achieve different technical goals. However, because they are both aimed at using private information without fully revealing it, they are often confused. To help draw a distinction between the two approaches, we will discuss the power and limitations of both and give typical scenarios in which each can be highly effective.

We are interested in scenarios in which multiple individuals (sometimes, society as a whole) can derive substantial utility from a computation on private data but, in order to preserve privacy, cannot simply share all of their data with each other or with an external party.

Secure multiparty computation

MPC methods allow a group of parties to collectively perform a computation that involves all of their private data while revealing only the result of the computation. More formally, an MPC protocol enables n parties, each of whom possesses a private dataset, to compute a function of the union of their datasets in such a way that the only information revealed by the computation is the output of the function. Common situations in which MPC can be used to protect private interests include

  • auctions: the winning bid amount should be made public, but no information about the losing bids should be revealed;
  • voting: the number of votes cast for each option should be made public but not the vote cast by any one individual;
  • machine learning inference: secure two-party computation enables a client to submit a query to a server that holds a proprietary model and receive a response, keeping the query private from the server and the model private from the client.
Related content
New approach to homomorphic encryption speeds up the training of encrypted machine learning models sixfold.

Note that the number n of participants can be quite small (e.g., two in the case of machine learning inference), moderate in size, or very large; the latter two size ranges both occur naturally in auctions and votes. Similarly, the participants may be known to each other (as they would be, for example, in a departmental faculty vote) or not (as, for example, in an online auction). MPC protocols mathematically guarantee the secrecy of input values but do not attempt to hide the identities of the participants; if anonymous participation is desired, it can be achieved by combining MPC with an anonymous-communication protocol.

Although MPC may seem like magic, it is implementable and even practical using cryptographic and distributed-computing techniques. For example, suppose that Alice, Bob, Carlos, and David are four engineers who want to compare their annual raises. Alice selects four random numbers that sum to her raise. She keeps one number to herself and gives each of the other three to one of the other engineers. Bob, Carlos, and David do the same with their own raises.

Secure multiparty computation
Four engineers wish to compute their average raise, without revealing any one engineer's raise to the others. Each selects four numbers that sum to his or her raise and sends three of them to the other engineers. Each engineer then sums his or her four numbers — one private number and three received from the others. The sum of all four engineers' sums equals the sum of all four raises.

After everyone has distributed the random numbers, each engineer adds up the numbers he or she is holding and sends the sum to the others. Each engineer adds up these four sums privately (i.e., on his or her local machine) and divides by four to get the average raise. Now they can all compare their raises to the team average.


Amount

Alice’s share

Bob’s share

Carlos’s share

David’s share

Sum of sums

Alice’s raise

3800

-1000

2500

900

1400


Bob’s raise

2514

700

400

650

764


Carlos’s raise

2982

750

-100

832

1500


David’s raise

3390

1500

900

-3000

3990


Sum

12686

1950

3700

-618

7654

12686

Average

3171.5





3171.5

Note that, because Alice (like Bob, Carlos, and David) kept part of her raise private (the bold numbers), no one else learned her actual raise. When she summed the numbers she was holding, the sum didn’t correspond to anyone’s raise. In fact, Bob’s sum was negative, because all that matters is that the four chosen numbers add up to the raise; the sign and magnitude of these four numbers are irrelevant.

Summing all of the engineers’ sums results in the same value as summing the raises directly, namely $12,686. If all of the engineers follow this protocol faithfully, dividing this value by four yields the team average raise of $3,171.50, which allows each person to compare his or her raise against the team average (locally and hence privately) without revealing any salary information.

A highly readable introduction to MPC that emphasizes practical protocols, some of which have been deployed in real-world scenarios, can be found in a monograph by Evans, Kolesnikov, and Rosulek. Examples of real-world applications that have been deployed include analysis of gender-based wage gaps in Boston-area companies, aggregate adoption of cybersecurity measures, and Covid exposure notification. Readers may also wish to read our previous blog post on this and related topics.

Differential privacy

Differential privacy (DP) is a body of statistical and algorithmic techniques for releasing an aggregate function of a dataset without revealing the mapping between data contributors and data items. As in MPC, we have n parties, each of whom possesses a data item. Either the parties themselves or, more often, an external agent wishes to compute an aggregate function of the parties’ input data.

Related content
Calibrating noise addition to word density in the embedding space improves utility of privacy-protected text.

If this computation is performed in a differentially private manner, then no information that could be inferred from the output about the ith input, xi, can be associated with the individual party Pi. Typically, the number n of participants is very large, the participants are not known to each other, and the goal is to compute a statistical property of the set {x1, …, xn} while protecting the privacy of individual data contributors {P1, …, Pn}.

In slightly more detail, we say that a randomized algorithm M preserves differential privacy with respect to an aggregation function f if it satisfies two properties. First, for every set of input values, the output of M closely approximates the value of f. Second, for every distinct pair (xi, xi') of possible values for the ith individual input, the distribution of M(x1, …, xi,…, xn) is approximately equivalent to the distribution of M(x1, …, xi′, …, xn). The maximum “distance” between the two distributions is characterized by a parameter, ϵ, called the privacy parameter, and M is called an ϵ-differentially private algorithm.

Note that the output of a differentially private algorithm is a random variable drawn from a distribution on the range of the function f. That is because DP computation requires randomization; in particular, it works by “adding noise.” All known DP techniques introduce a salient trade-off between the privacy parameter and the utility of the output of the computation. Smaller values of ϵ produce better privacy guarantees, but they require more noise and hence produce less-accurate outputs; larger values of ϵ yield worse privacy bounds, but they require less noise and hence deliver better accuracy.

For example, consider a poll, the goal of which is to predict who is going to win an election. The pollster and respondents are willing to sacrifice some accuracy in order to improve privacy. Suppose respondents P1, …, Pn have predictions x1, …, xn, respectively, where each xi is either 0 or 1. The poll is supposed to output a good estimate of p, which we use to denote the fraction of the parties who predict 1. The DP framework allows us to compute an accurate estimate and simultaneously to preserve each respondent’s “plausible deniability” about his or her true prediction by requiring each respondent to add noise before sending a response to the pollster.

Related content
Private aggregation of teacher ensembles (PATE) leads to word error rate reductions of more than 26% relative to standard differential-privacy techniques.

We now provide a few more details of the polling example. Consider the algorithm m that takes as input a bit xi and flips a fair coin. If the coin comes up tails, then m outputs xi; otherwise m flips another fair coin and outputs 1 if heads and 0 if tails. This m is known as the randomized response mechanism; when the pollster asks Pi for a prediction, Pi responds with m(xi). Simple statistical calculation shows that, in the set of answers that the pollster receives from the respondents, the expected fraction that are 1’s is

Pr[First coin is tails] ⋅ p + Pr[First coin is heads] ⋅ Pr[Second coin is heads] = p/2 + 1/4.

Thus, the expected number of 1’s received is n(p/2 + 1/4). Let N = m(x1) + ⋅⋅⋅ + m(xn) denote the actual number of 1’s received; we approximate p by M(x1, …, xn) = 2N/n − 1/2. In fact, this approximation algorithm, M, is differentially private. Accuracy follows from the statistical calculation, and privacy follows from the “plausible deniability” provided by the fact that M outputs 1 with probability at least 1/4 regardless of the value of xi.

Differential privacy has dominated the study of privacy-preserving statistical computation since it was introduced in 2006 and is widely regarded as a fundamental breakthrough in both theory and practice. An excellent overview of algorithmic techniques in DP can be found in a monograph by Dwork and Roth. DP has been applied in many real-world applications, most notably the 2020 US Census.

The power and limitations of MPC and DP

We now review some of the strengths and weaknesses of these two approaches and highlight some key differences between them.

Secure multiparty computation

MPC has been extensively studied for more than 40 years, and there are powerful, general results showing that it can be done for all functions f using a variety of cryptographic and coding-theoretic techniques, system models, and adversary models.

Despite the existence of fully general, secure protocols, MPC has seen limited real-world deployment. One obstacle is protocol complexity — particularly the communication complexity of the most powerful, general solutions. Much current work on MPC addresses this issue.

Related content
A privacy-preserving version of the popular XGBoost machine learning algorithm would let customers feel even more secure about uploading sensitive data to the cloud.

More-fundamental questions that must be answered before MPC can be applied in a given scenario include the nature of the function f being computed and the information environment in which the computation is taking place. In order to explain this point, we first note that the set of participants in the MPC computation is not necessarily the same as the set of parties that receive the result of the computation. The two sets may be identical, one may be a proper subset of the other, they may have some (but not all) elements in common, or they may be entirely disjoint.

Although a secure MPC protocol (provably!) reveals nothing to the recipients about the private inputs except what can be inferred from the result, even that may be too much. For example, if the result is the number of votes for and votes against a proposition in a referendum, and the referendum passes unanimously, then the recipients learn exactly how each participant voted. The referendum authority can avoid revealing private information by using a different f, e.g., one that is “YES” if the number of votes for the proposition is at least half the number of participants and “NO” if it is less than half.

This simple example demonstrates a pervasive trade-off in privacy-preserving computation: participants can compute a function that is more informative if they are willing to reveal private information to the recipients in edge cases; they can achieve more privacy in edge cases if they are willing to compute a less informative function.

In addition to specifying the function f carefully, users of MPC must evaluate the information environment in which MPC is to be deployed and, in particular, must avoid the catastrophic loss of privacy that can occur when the recipients combine the result of the computation with auxiliary information. For example, consider the scenario in which the participants are all of the companies in a given commercial sector and metropolitan area, and they wish to use MPC to compute the total dollar loss that they (collectively) experienced in a given year that was attributable to data breaches; in this example, the recipients of the result are the companies themselves.

Related content
Scientists describe the use of privacy-preserving machine learning to address privacy challenges in XGBoost training and prediction.

Suppose further that, during that year, one of the companies suffered a severe breach that was covered in the local media, which identified the company by name and reported an approximate dollar figure for the loss that the company suffered as a result of the breach. If that approximate figure is very close to the total loss imposed by data breaches on all the companies that year, then the participants can conclude that all but one of them were barely affected by data breaches that year.

Note that this potentially sensitive information is not leaked by the MPC protocol, which reveals nothing but the aggregate amount lost (i.e., the value of the function f). Rather, it is inferred by combining the result of the computation with information that was already available to the participants before the computation was done. The same risk that input privacy will be destroyed when results are combined with auxiliary information is posed by any computational method that reveals the exact value of the function f.

Differential privacy

The DP framework provides some elegant, simple mechanisms that can be applied to any function f whose output is a vector of real numbers. Essentially, one can independently perturb or “noise up” each component of f(x) by an appropriately defined random value. The amount of noise that must be added in order to hide the contribution (or, indeed, the participation) of any single data subject is determined by the privacy parameter and the maximum amount by which a single input can change the output of f. We explain one such mechanism in slightly more mathematical detail in the following paragraph.

One can apply the Laplace mechanism with privacy parameter ϵ to a function f, whose outputs are k-tuples of real numbers, by returning the value f(x1, …, xn) + (Y1, …, Yk) on input (x1, …, xn), where the Yi are independent random variables drawn from the Laplace distribution with parameter Δ(f)/ϵ. Here Δ(f) denotes the ℓ1sensitivity of the function f, which captures the magnitude by which a single individual’s data can change the output of f in the worst case. The technical definition of the Laplace distribution is beyond the scope of this article, but for our purposes, its important property is that the Yi can be sampled efficiently.

Related content
The team’s latest research on privacy-preserving machine learning, federated learning, and bias mitigation.

Crucially, DP protects data contributors against privacy loss caused by post-processing computational results or by combining results with auxiliary information. The scenario in which privacy loss occurred when the output of an MPC protocol was combined with information from an existing news story could not occur in a DP application; moreover, no harm could be done by combining the result of a DP computation with auxiliary information in a future news story.

DP techniques also benefit from powerful composition theorems that allow separate differentially private algorithms to be combined in one application. In particular, the independent use of an ϵ1-differentially private algorithm and an ϵ2-differentially private algorithm, when taken together, is (ϵ1 + ϵ2)-differentially private.

One limitation on the applicability of DP is the need to add noise — something that may not be tolerable in some application scenarios. More fundamentally, the ℓ1 sensitivity of a function f, which yields an upper bound on the amount of noise that must be added to the output in order to achieve a given privacy parameter ϵ, also yields a lower bound. If the output of f is strongly influenced by the presence of a single outlier in the input, then it is impossible to achieve strong privacy and high accuracy simultaneously.

For example, consider the simple case in which f is the sum of all of the private inputs, and each input is an arbitrary positive integer. It is easy to see that the ℓ1 sensitivity is unbounded in this case; to hide the contribution or the participation of an individual whose data item strongly dominates those of all other individuals would require enough noise to render the output meaningless. If one can restrict all of the private inputs to a small interval [a,b], however, then the Laplace mechanism can provide meaningful privacy and accuracy.

DP was originally designed to compute statistical aggregates while preserving the privacy of individual data subjects; in particular, it was designed with real-valued functions in mind. Since then, researchers have developed DP techniques for non-numerical computations. For example, the exponential mechanism can be used to solve selection problems, in which both input and output are of arbitrary type.

Related content
Amazon is helping develop standards for post-quantum cryptography and deploying promising technologies for customers to experiment with.

In specifying a selection problem, one must define a scoring function that maps input-output pairs to real numbers. For each input x, a solution y is better than a solution y′ if the score of (x,y) is greater than that of (x,y′). The exponential mechanism generally works well (i.e., achieves good privacy and good accuracy simultaneously) for selection problems (e.g., approval voting) that can be defined by scoring functions of low sensitivity but not for those (e.g., set intersection) in which the scoring function must have high sensitivity. In fact, there is no differentially private algorithm that works well for set intersection; by contrast, MPC for set intersection is a mature and practical technology that has seen real-world deployment.

Conclusion

In conclusion, both secure multiparty computation and differential privacy can be used to perform computations on sensitive data while preserving the privacy of those data. Important differences between the bodies of technique include

  • The nature of the privacy guarantee: Use of MPC to compute a function y = f(x1, x2, ..., xn) guarantees that the recipients of the result learn the output y and nothing more. For example, if there are exactly two input vectors that are mapped to y by f, the recipients of the output y gain no information about which of two was the actual input to the MPC computation, regardless of the number of components in which these two input vectors differ or the magnitude of the differences. On the other hand, for any third input vector that does not map to y, the recipient learns with certainty that the real input to the MPC computation was not this third vector, even if it differs from one of the first two in only one component and only by a very small amount. By contrast, computing f with a DP algorithm guarantees that, for any two input vectors that differ in only one component, the (randomized!) results of the computation are approximately indistinguishable, regardless of whether the exact values of f on these two input vectors are equal, nearly equal, or extremely different. Straightforward use of composition yields a privacy guarantee for inputs that differ in c components at the expense of increasing the privacy parameter by a factor of c.
  • Typical use cases: DP techniques are most often used to compute aggregate properties of very large datasets, and typically, the identities of data contributors are not known. None of these conditions is typical of MPC use cases.
  • Exact vs. noisy answers: MPC can be used to compute exact answers for all functions f. DP requires the addition of noise. This is not a problem in many statistical computations, but even small amounts of noise may not be acceptable in some application scenarios. Moreover, if f is extremely sensitive to outliers in the input data, the amount of noise needed to achieve meaningful privacy may preclude meaningful accuracy.
  • Auxiliary information: Combining the result of a DP computation with auxiliary information cannot result in privacy loss. By contrast, any computational method (including MPC) that returns the exact value y of a function f runs the risk that a recipient of y might be able to infer something about the input data that is not implied by y alone, if y is combined with auxiliary information.

Finally, we would like to point out that, in some applications, it is possible to get the benefits of both MPC and DP. If the goal is to compute f, and g is a differentially private approximation of f that achieves good privacy and accuracy simultaneously, then one natural way to proceed is to use MPC to compute g. We expect to see both MPC and DP used to enhance data privacy in Amazon’s products and services.

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.