Amazon Redshift re-invented research paper and photos of Rahul Pathak, vice president of analytics at AWS, and Ippokratis Pandis, AWS senior principal engineer
The "Amazon Redshift re-invented" research paper will be presented at a leading database conference next month. Two of the paper's authors, Rahul Pathak (top right), vice president of analytics at AWS, and Ippokratis Pandis (bottom right), an AWS senior principal engineer, discuss the origins of Redshift, how the system has evolved in the past decade, and where they see the service evolving in the years ahead.

Amazon Redshift: Ten years of continuous reinvention

Two authors of Amazon Redshift research paper that will be presented at leading international forum for database researchers reflect on how far the first petabyte scale cloud data warehouse has advanced since it was announced ten years ago.

Nearly ten years ago, in November 2012 at the first-ever Amazon Web Services (AWS) re:Invent, Andy Jassy, then AWS senior vice president, announced the preview of Amazon Redshift, the first fully managed, petabyte-scale cloud data warehouse. The service represented a significant leap forward from traditional on-premises data warehousing solutions, which were expensive, inflexible, and required significant human and capital resources to operate.

In a blog post on November 28, 2012, Werner Vogels, Amazon chief technical officer, highlighted the news: “Today, we are excited to announce the limited preview of Amazon Redshift, a fast and powerful, fully managed, petabyte-scale data warehouse service in the cloud.”

Further in the post, Vogels added, “The result of our focus on performance has been dramatic. Amazon.com’s data warehouse team has been piloting Amazon Redshift and comparing it to their on-premise data warehouse for a range of representative queries against a two billion row data set. They saw speedups ranging from 10x – 150x!”

That’s why, on the day of the announcement, Rahul Pathak, then a senior product manager, and the entire Amazon Redshift team were confident the product would be popular.

“But we didn’t really understand how popular,” he recalls.

“At preview we asked customers to sign up and give us some indication of their data volume and workloads,” Pathak, now vice president of Relational Engines at AWS, said. “Within about three days we realized that we had ten times more demand for Redshift than we had planned for the entire first year of the service. So we scrambled right after re:Invent to accelerate our hardware orders to ensure we had enough capacity on the ground for when the product became generally available in early 2013. If we hadn’t done that preview, we would have been caught short.”

The Redshift team has been sprinting to keep apace of customer demand ever since. Today, the service is used by tens of thousands of customers to process exabytes of data daily. In June a subset of the team will present the paper “Amazon Redshift re-invented ” at a leading international forum for database researchers, practitioners, and developers, the ACM SIGMOD/PODS Conference in Philadelphia.

Related content
Amazon DynamoDB was introduced 10 years ago today; one of its key contributors reflects on its origins, and discusses the 'never-ending journey' to make DynamoDB more secure, more available and more performant.

The paper highlights four key areas where Amazon Redshift has evolved in the past decade, provides an overview of the system architecture, describes its high-performance transactional storage and compute layers, details how smart autonomics are provided, and discusses how AWS and Redshift make it easy for customers to use the best set of services to meet their needs.

Amazon Science recently connected with two of the paper’s authors, Pathak, and Ippokratis Pandis, an AWS senior principal engineer, to discuss the origins of Redshift, how the system has evolved over the past decade, and where they see the service evolving in the years ahead.

  1. Q. 

    Can you provide some background on the origin story for Redshift? What were customers seeking, and how did the initial version address those needs?

    A. 

    Rahul: We had been meeting with customers who in the years leading up to the launch of Amazon Redshift had moved just about every workload they had to the cloud except for their data warehouse. In many cases, it was the last thing they were running on premises, and they were still dealing with all of the challenges of on-premises data warehouses. They were expensive, had punitive licensing, were hard to scale, and customers couldn’t analyze all of their data. Customers told us they wanted to run data warehousing at scale in the cloud, that they didn’t want to compromise on performance or functionality, and that it had to be cost-effective enough for them to analyze all of their data.

    So, this is what we started to build, operating under the code name Cookie Monster. This was at a time when customers’ data volumes were exploding, and not just from relational databases, but from a wide variety of sources. One of our early private beta customers tried it and the results came back so fast they thought the system was broken. It was about 10 to 20 times faster than what they had been using before. Another early customer was pretty unhappy with gaps in our early functionality. When I heard about their challenges, I got in touch, understood their feedback, and incorporated it into the service before we made it generally available in February 2013. This customer soon turned into one of our biggest advocates.

    When we launched the service and announced our pricing at $1000 a terabyte per year, people just couldn’t believe we could offer a product with that much capability at such a low price point. The fact that you could provision a data warehouse in minutes instead of months also caught everyone’s attention. It was a real game-changer for this industry segment.

    Ippokratis: I was at IBM Research at the time working on database technologies there, and we recognized that providing data warehousing as a cloud service was a game changer. It was disruptive. We were working with customers’ on-premises systems where it would take us several days or weeks to resolve an issue, whereas with a cloud data warehouse like Redshift, it would take minutes. It was also apparent that the rate of innovation would accelerate in the cloud.

    In the on-premises world, it was taking months if not years to get new functionality into a software release, whereas in the cloud new capabilities could be introduced in weeks, without customers having to change a single line of code in their consuming applications. The Redshift announcement was an inflection point; I got really interested in the cloud, and cloud data warehouses, and eventually joined Amazon [Ippokratis joined the Redshift team as a principal engineer in Oct. 2015].

  2. Q. 

    How has Amazon Redshift evolved over the past decade since the launch nearly 10 years ago?

    A. 

    Ippokratis: As we highlight in the paper, the service has evolved at a rapid pace in response to customers’ needs. We focused on four main areas: 1) customers’ demand for high-performance execution of increasingly complex analytical queries; 2) our customers’ need to process more data and significantly increase the number of users who need to derive insights from that data; 3) customers’ need for us to make the system easier to use; and 4) our customers’ desire to integrate Redshift with other AWS services, and the AWS ecosystem. That’s a lot, so we’ll provide some examples across each dimension.

    Related publication
    Enterprise companies use spatial data for decision optimization and gain new insights regarding the locality of their business and services. Industries rely on efficiently combining spatial and business data from different sources, such as data warehouses, geospatial information systems, transactional systems, and data lakes, where spatial data can be found in structured or unstructured form. In this demonstration

    Offering the leading price performance has been our primary focus since Rahul first began working on what would become Redshift. From the beginning, the team has focused on making core query execution latency as low as possible so customers can run more workloads, issue more jobs into the system, and run their daily analysis. To do this, Redshift generates C++ code that is highly optimized and then sends it to the distributor in the parallel database and executes this highly optimized code. This makes Redshift unique in the way it executes queries, and it has always been the core of the service.

    We have never stopped innovating here to deliver our customers the best possible performance. Another thing that’s been interesting to me is that in the traditional business intelligence (BI) world, you optimize your system for very long-running jobs. But as we observe the behavior of our customers in aggregate, what’s surprising is that 90 percent of our queries among the billions we run daily in our service execute in less than one second. That’s not what people had traditionally expected from a data warehouse, and that has changed the areas of the code that we optimize.

    Rahul: As Ippokratis mentioned, the second area we focused on in the paper was customers’ need to process more data and to use that data to drive value throughout the organization. Analytics has always been super important, but eight or ten years ago it wasn’t necessarily mission critical for customers in the same way transactional databases were. That has definitely shifted. Today, core business processes rely on Redshift being highly available and performant. The biggest architectural change in the past decade in support of this goal was the introduction of Redshift Managed Storage, which allowed us to separate compute and storage, and focus a lot of innovation in each area.

    Diagram of the Redshift Managed Storage
    The Redshift managed storage layer (RMS) is designed for a durability of 99.999999999% and 99.99% availability over a given year, across multiple availability zones. RMS manages both user data as well as transaction metadata.

    Another big trend has been the desire of customers to query across and integrate disparate datasets. Redshift was the first data warehouse in the cloud to query Amazon S3 data, that was with Redshift Spectrum in 2017. Then we demonstrated the ability to run a query that scanned an exabyte of data in S3 as well as data in the cluster. That was a game changer.

    Customers like NASDAQ have used this extensively to query data that’s on local disk for the highest performance, but also take advantage of Redshift’s ability to integrate with the data lake and query their entire history of data with high performance. In addition to querying the data lake, integrated querying of transactional data stores like Aurora and RDS has been another big innovation, so customers can really have a high-performance analytics system that’s capable of transparently querying all of the data that matters to them without having to manage these complex integration processes that other systems require.

    Illustration of how a query flows through Redshift.
    This diagram from the research paper illustrates how a query flows through Redshift. The sequence is described in detail on pages 2 and 3 of the paper.

    Ippokratis: The third area we focused on in the paper was ease of use. One change that stands out for me is that on-premises data warehousing required IT departments to have a DBA (data base administrator) who would be responsible for maintaining the environment. Over the past decade, the expectation from customers has evolved. Now, if you are offering data warehousing as a service, the systems must be capable of auto tuning, auto healing, and auto optimizing. This has become a big area of focus for us where we incorporate machine learning and automation into the system to make it easier to use, and to reduce the amount of involvement required of administrators.

    Rahul: In terms of ease of use, three innovations come to mind. One is concurrency scaling. Similar to workload management, customers would previously have to manually tweak concurrency or reset clusters of the manually split workloads. Now, the system automatically provisions new resources and scales up and down without customers having to take any action. This is a great example of how Redshift has gotten much more dynamic and elastic.

    The second ease of use innovation is automated table optimization. This is another place where the system is able to observe workloads and data layouts and automatically suggest how data should be sorted and distributed across nodes in the cluster. This is great because it’s a continuously learning system so workloads are never static in time.

    Related publication
    How should we split data among the nodes of a distributed data warehouse in order to boost performance for a forecasted workload? In this paper, we study the effect of different data partitioning schemes on the overall network cost of pairwise joins. We describe a generally-applicable data distribution framework initially designed for Amazon Redshift, a fully-managed petabyte-scale data warehouse in the

    Customers are always adding more datasets, and adding more users, so what was optimal yesterday might not be optimal tomorrow. Redshift observes this and modifies what's happening under the covers to balance that. This was the focus of a really interesting graph optimization paper that we wrote a few years ago about how to analyze for optimal distribution keys for how data is laid out within a multi-node parallel-processing system. We've coupled this with automated optimization and then table encoding. In an analytics system, how you compress data has a big impact because the less data you scan, the faster your queries go. Customers had to reason about this in the past. Now Redshift can automatically determine how to encode data correctly to deliver the best possible performance for the data and the workload.

    The third innovation I want to highlight here is Amazon Redshift Serverless, which we launched in public preview at re:Invent last fall. Redshift Serverless removes all of the management of instances and clusters, so customers can focus on getting to insights from data faster and not spend time managing infrastructure. With Redshift Serverless, customers can simply provision an endpoint and begin to interact with their data, and Redshift Serverless will auto scale and automatically manage the system to essentially remove all of that complexity from customers.

    Customers can just focus on their data, set limits to manage their budgets, and we deliver optimal performance between those limits. This is another massive step forward in terms of ease of use because it eliminates any operations for customers. The early response to the preview has been tremendous. Thousands of customers have been excited to put Amazon Redshift Serverless through its paces over the past few months, and we’re excited about making it generally available in the near future.

    Amazon Redshift architecture diagram
    The Amazon Redshift architecture as presented in the research paper.

    Ippokratis: A fourth area of focus in the paper is on integration with other AWS services, and the AWS ecosystem. Integration is another area where customer behavior has evolved from traditional BI use cases. Today, cloud data warehouses are a central hub with tight integration with a broader set of AWS services. We provided the ability for customers to join data from the warehouse with the data lake. Then customers said they needed access to high-velocity business data in operational databases like Aurora and RDS, so we provided access to these operational data stores. Then we added support for streams, as well as integration with SageMaker and Lambda so customers can run machine learning training and inference without moving their data, and do generic compute. As a result, we’ve converted the traditional BI system into a well-integrated set of AWS services.

    Rahul: One big area of integration has been with our machine-learning ecosystem. With Redshift ML we have enabled anyone who knows SQL to take advantage of all of our machine-learning innovation. We built the ability to create a model from the SQL prompt, which gets the data into Amazon S3 and calls Amazon SageMaker, to use automated machine learning to build the most appropriate model to provide predictions on the data.

    This model is compiled efficiently and brought back into the data warehouse for customers to run very high-performance parallel inferences with no additional compute or no extra cost. The beauty of this integration is that every innovation we make within SageMaker means that Redshift ML gets better as well. This is just another means by which customers benefit from us connecting our services together.

    Related content
    Amazon researchers describe new method for distributing database tables across servers.

    Another big area for integration has been data sharing. Once we separated storage and compute layers with RA3 instances, we could enable data sharing, giving customers the ability to share data with clusters in the same account, and other accounts, or across regions. This allows us to separate consumers from producers of data, which enables things like modern data mesh architectures. Customers can share data without data copying, so they are transactionally consistent across accounts.

    For example, users within a data-science organization can securely work from the shared data, as can users within the reporting or marketing organization. We’ve also integrated data sharing with AWS Data Exchange, so now customers can search for — and subscribe to — third-party datasets that are live, up to date, and can be queried immediately in Redshift. This has been another game changer from the perspective of setting data free, enabling data monetization for third-party providers, and secure and live data access and licensing for subscribers for high-performance analytics within and across organizations. The fact that Redshift is part of an incredibly rich data ecosystem is a huge win for customers, and in keeping with customers’ desire to make data more pervasively available across the company.

  3. Q. 

    You indicate in the paper that Redshift innovation is continuing at an accelerated pace.  How do you see the cloud data warehouse segment evolving – and more specifically Redshift – over the next several years?

    A. 

    Rahul: A few things will continue to be true as we head into the future. Customers will be generating ever more amounts of data, and they’re going to want to analyze that data more cost effectively. Data volumes are growing exponentially, but obviously customers don't want their costs growing exponentially. This requires that we continue to innovate, and find new levels of performance to ensure that the cost of processing a unit of data continues to go down.

    We’ll continue innovating in software, in hardware, in silicon, and in using machine learning to make sure we deliver on that promise for customers. We’ve delivered on that promise for the past 10 years, and we’ll focus on making sure we deliver on that promise into the future.

    I’m very proud of what the team has accomplished, but equally as excited about all the things we’re going to do to improve Redshift in the future.
    Ippokratis Pandis

    Also, customers are always going to want better availability, they’re always going to want their data to be secure, and they’re always going to want more integrations with more data sources, and we intend to continue to deliver on all of those. What will stay the same is our ability to offer the-best in-segment price performance and capabilities, and the best-in-segment integration and security because they will always deliver value for customers.

    Ippokratis: It has been an incredible journey; we have been rebuilding the plane as we’ve been flying it with customers onboard, and this would not have happened without the support of AWS leadership, but most importantly the tremendous engineers, managers, and product people who have worked on the team.

    As we did in the paper, I want to recognize the contributions of Nate Binkert and Britt Johnson, who have passed, but whose words of wisdom continue to guide us. We’ve taken data warehousing, what we learned from books in school (Ippokratis earned his PhD in electrical and computer engineering from Carnegie Mellon University) and brought it to the cloud. In the process, we’ve been able to innovate, and write new pages in the book. I’m very proud of what the team has accomplished, but equally as excited about all the things we’re going to do to improve Redshift in the future.

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.