This picture shows the HVAC system on the rooftop of a skyscraper
Facility energy optimization provides an organization’s facilities team low-hanging-fruit opportunities for reducing costs and carbon. Data-driven analysis can help to identify fault detection and drive energy efficiencies for facilities management.

Data-driven fault identification is key to more sustainable facilities management

How data-driven analysis can help to identify fault detection and drive energy efficiencies for facilities of all sizes.

In a previous article on sustainable buildings, we talked about the approach of “sense, act, and scale” to drive efficiencies in buildings, and provided information using scientific publications. In this article, we will explore how data-driven analysis can help to identify fault detection and drive energy efficiencies for facilities management by providing details on:

  • Key challenges for building management and operations;
  • Building system design fundamentals;
  • Key data points to investigate faults for facilities-level sustainability; and
  • Data-driven fault identification on AWS

Global temperatures are on the rise, greenhouse gas (GHG) emissions are the primary contributor, and facilities are among the top contributors to GHG. As stipulated in the Paris Agreement, facilities need to be 30% more energy efficient and net carbon neutral by 2050. Many companies have set new targets to reduce their emissions in recent years. For example, Amazon has set out the mission to be net neutral by 2040 and, in its recent sustainability report, has touched on how the company is using innovative design to build sustainability into physical Amazon campuses.

NeurIPS competition involves reinforcement learning, with the objective of minimizing both cost and CO2 emissions.

This article provides information on how companies of all sizes can operate and maintain their existing buildings more efficiently by identifying and fixing faults using data-driven mechanisms. In this vein, Amazon is sponsoring an AI challenge at NeurIPS this year that focuses on building energy management in a smart grid. Bottom line: energy optimization of facilities must be a key component of your organization’s plan to operate more sustainably.

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

Facility energy optimization provides an organization’s facilities team low-hanging-fruit opportunities for reducing costs and carbon. However, building systems do inherit many complexities that must be addressed.

Some of the key facilities-management challenges are:

  • A building’s lifespan is 50+ years, and a facility’s system sensors are typically installed on day one. Many new cloud-native sensor options come to market every year, but building management systems (BMS) aren’t open, making it difficult to modernize data architectures for building infrastructure;
  • Across any large real estate portfolio there is a wide range of technology, standards, building types, and designs that are difficult to manage over their lifecycles; 
  • Building management and automation systems require a third party to own and modify production data, and licensing fees aren’t based on consumption pricing; and 
  • Facilities teams generally lack the cloud expertise required to design a bespoke management solution, and their IT teams often don’t have product-level experience to provide as an alternative for addressing building-management needs.

Facilities management and sustainability

Facilities management teams have limited options to modify most core BMS functions.

These systems are sometimes referred to as black boxes in that they don’t have the same level of do-it-yourself features that most cloud users have come to expect. There can be contractual challenges, as well, for building tenants who don’t have access to BMS information. This is by design, primarily due to a clear operational argument that safety and security control functions should be limited to key personnel. However, this lack of access to building-performance analytics, required for enterprise-level sustainability transformations, is increasingly considered a blocker by many of our sustainability customers.

Let’s begin our analysis by looking at a building’s biggest consumer of electricity and producer of emissions: the HVAC system.

HVAC units are central to a building and constitute roughly 50% of a building’s energy consumption. As a result, they are well instrumented and generally follow a rules-based approach. The downside: this approach can lead to many false alarms and building managers rely on manual inspection and occupants to communicate important faults that require attention. Building managers and engineers focus significant time and budget on HVAC systems, but nevertheless HVAC system faults still can account for 5% to 20% of energy waste.

The most common example of an HVAC unit with which we are all familiar is an air conditioner. In a BMS, HVAC is comprised of sub-components that provide heating or cooling, ventilation (air handling units, fans) and AC (rooftop units, variable refrigerants) and more.

HVAC Units 2_220830211027 (1).png

A building’s data model, and the larger building management schema, are established when the building first opens. Alerts, alarms, and performance data are issued through the BMS and a manager will notify a building services team to take action as needed. However, as the building and infrastructure ages many alarms become endemic and are difficult to remedy. Alarm fatigue is a term often used to describe the resulting BMS operator experience.

Variable air volume (VAV) units are another important asset that help to maintain temperatures by managing local air flow. VAV units help optimize the temperature by modifying air flow as opposed to conventional air volume (CAV) units which provide a constant volume of air that only affects air temperature.

There are often hundreds of VAV units in a larger building and managing them is burdensome. Building engineers have limited time to configure each of them as building demands change and VAV unit configurations are typically left unchanged after the commissioning of the building. The result: many unseen or mysterious building faults, and the hidden loss of energy over the years.

Related content
Confronting climate change requires the participation of governments, companies, academics, civil-society organizations, and the public.

Many modern buildings are designed to accommodate whatever the building planners know at the time of commissioning. As a result, HVAC system configuration isn’t a data-driven process because operational data doesn’t yet exist. The only real incentives for HVAC system optimization typically result from failures and occupant complaints. To meet future sustainability targets, buildings must be equipped with data-driven smart configurations that can be adjusted automatically.

To achieve this, we must understand the fundamentals of air flow as we need to combine the expertise of building engineers, IoT engineers, and data engineers to resolve some of the complex air-flow challenges. This also requires an understanding of how facilities are generally managed today, which we’ll examine next.

Anatomy of facilities management

The image below shows how an air-handling unit (AHU) uses fans to distribute air through ducting. These ducts are attached to AHUs (a type of VAV unit), controlling the flow of air to specific rooms.

typical air distribution topology.png
BMS software provides tools to help operators define logical “zones” that virtually represent a given physical space. This zone approach is useful in helping operators analyze the effectiveness of a given cooling design relative to the operational requirements.

To change the temperature of a given zone (often representing a physical room), a sensor will send a notification through a building gateway and controller. This device serves as an intermediary between the BMS server and a given HVAC unit.

There is some automation built into these HVAC systems in the form of thermostats. The automation comes in the form of a given cooling unit responding to a temperature reading, calculated by the thermostat. These setpoints provide a temperature range that, when followed, provide the best performance of the system.

Setpoint typically refers to the point at which a building system is set to activate or deactivate, eg a heating system might be set to switch on if the internal temperature falls below 20°C.

VAV Terminal_220906154354.png
A controller in the VAV unit is attached to the room thermostat. Thermostats tells VAV terminals if zone temperatures are too hot, cold, or just right. The VAV unit has several key components inside: controller, actuator, damper, shaft, and reheat coil.

AHU and VAV unit control points are managed by BMS software. This software is vendor managed and the configuration of the control system is determined at building inception. The configurations can be established based on several factors: room capacity and occupancy, room location, room cooling requirement, zone requirement, and more.

To illustrate a data model that reflects the operation of the HVAC system, let’s look at the VAVs that help distribute the air and the fault-driven alerts apparent in most aging systems. It is difficult to personalize these configurations as they are not data driven and do not update automatically. Let's use the flow of air through a given building as a use case and assume its operation will have a sizable impact on the building's overall energy usage.

Damper Side-by-side_v2_220919101743.png
On the left, the damper is fully open because it is a summer day, it is hot outside, and the room is full of people. But on the right, the damper is partially open because it is a winter day and there are no people in the room, requiring minimum heat load.

There will often be multiple zone-specific faults, such as temperature or flow failures, issues with dampers or fans, software configuration errors that can lead to short-cycling of the unit(s), and communication or controller problems, which make it difficult to even identify the problem remotely. These factors all result in a low-efficiency cooling system that increases emissions, wasting energy and money.

What faults can tell you about sustainable building performance

Faults can be neglected for long periods of time, leaking invisible energy in the process.

Researchers from UC San Diego conducted a detailed data analysis (Bharathan was a co-author) of a 145,000-square-foot building. They identified 88 faults after building engineers fixed all the issues they could find. The paper estimates that fixing these faults could save 410.3 megawatt hours per year and, at a typical electrical cost of 12 cents per kilowatt hour, achieve a $492,360 savings in the first year.

According to the U.S. Environmental Protection Agency’s Greenhouse Gas Equivalencies Calculator, that’s the equivalent of 38,244 passenger car trips abated. Cisco offers another example. The company achieved a 28% reduction in electrical usage in their buildings worldwide by using an IP-Enabled Energy Management solution.

Traditional fault fixing focuses on the centralized HVAC subsystems such as AHU. Here we focus on the VAV units that are often ignored. Some of the key issues in VAV units are: air supply flow, temperature setpoints, thermostat adjustments, inappropriate cooling or stuck dampers.

Related content
Pioneering web-based PackOpt tool has resulted in an annual reduction in cardboard waste of 7% to 10% in North America, saving roughly 60,000 tons of cardboard annually.

To identify these faults, you can perform data analysis with key data attributes including temperature, heating, and cooling setpoints; upper- and lower- limit changes based on day of week; re-heat coil (on or off); occupancy sensor and settings (occupied, standby or unoccupied); damper sensor and damper settings; and pressure flow.

Using these parameters, we can define informative models. For example, you can create setpoints informed by seasonal weather data, in addition to room thermostats. You also can perform temperature data analysis against known occupancy times.

Data analysis isn’t easy at first; it’s generally not in a state where it can be readily loaded into a graph store. Oftentimes there is a lot of data transformation and IoT work required to get the data to a place where it can be analyzed by data scientists. To solve this challenge, you will need data experts, FM domain experts, cloud engineers, and someone who can bring them together to drive the right focus.

To begin, the best approach is setting up a meeting between your facilities and IT teams to start examining your building data. Some teams may grant you read-only access to the system. Otherwise, from a .CSV download of the last two to three years of building data, you can perform your analysis.

For data- driven fault identification within your facilities data, you can get started by using the Model, Cluster, and Compare (MCC approach). The primary objective of MCC is to determine clusters of zones within a building, and then use these clusters to automatically determine misconfigured, anomalous, or faulty zone controller configuration.

MCC approach to data-driven analysis

We will use a university-building example to explain the benefits of the MCC approach. The university building comprised personal offices, shared offices, kitchens, and restrooms.

In a typical room, the HVAC provides cold air during the summer. The supplied air flow is modulated to maintain the required temperature during day time, and falls back to a minimum during the night.

In the graph below, we show a room where the opposite happens because of a misconfiguration fault.

Supply Flow Graphic 1_220831110607.png
The VAV unit cools the room at night, but uses a minimal air flow during the day. The cooling temperature setpoint is 80°F from midnight until 10 a.m., and then drops to 75°F as expected. However, there is a continuous cold air supply flow of 800 cubic feet per minute (CFM) throughout the night until 11:30 a.m.

The building management contractor surmised these errors were caused due to a misunderstanding at the time of initial building commissioning. This fault was hidden within the system for years, and was identified while doing an MCC analysis.

Model

When we try to identify faults with raw sensor data, it often leads to misleading results. For example, a simple fault detection rule may generate an alarm if the temperature of a room goes beyond a threshold. The alarm may be false for any number of reasons: it could be a particularly hot day, or an event is occurring in the room. We need to look for faults that are consistent, and require human attention. Given the large number of alarms that are triggered with simple rules, such faults get overlooked.

Our MCC algorithm looks for rooms that behave differently from others over a long time-span. To compare different rooms, we create a model that captures the generic patterns of usage over months or years. Then we can compare and cluster rooms to weed out the faults.

In our algorithm, we use the measured room temperature and air flow from the HVAC to create a room energy model. The energy spent by the HVAC system on a room is proportional to the product of its temperature and airflow supplied as per the laws of thermodynamics. We use the product of two sensor measurements as the parameter to model the room because it indicates the generic patterns of use. If we find rooms whose energy patterns are substantially different, we can inspect them further.

Cluster

Room temperatures can fluctuate for natural reasons, and our fault-detection algorithm should not flag them.

The MCC algorithm clusters rooms that are similar to each other with the KMeans algorithm. The clusters naturally align rooms that are similar, for example, west-facing rooms, east-facing rooms, kitchenettes, and conference rooms. We can create these clusters manually, based on domain knowledge and usage type, or the clustering algorithm can automate this process.

Compare

Having defined configurations per cluster, the MCC algorithm then compares rooms to identify anomalies. This step ensures that natural fluctuations are ignored, and only the egregious rooms are highlighted, reducing the number of false alarms.

Intelligent rules

The MCC study created rules to detect new faults after analyzing the anomalies manually. Rules are a natural way to integrate with an existing system, and to catch similar faults that occur in the future. Rules are also interpretable by domain experts, enabling further tuning.

An interesting example of an identified fault is shown below:

Supply Flow Graphic 2_220831110647.png
The HVAC system strives to maintain the room temperature between the cooling setpoint (78F in this room) and the heating setpoint (74F). If the temperature goes beyond these setpoints, it will cool/heat the room as required. The room is excessively cooled with high air flow (800 CFM), causing the room temperature to fall below the heating setpoint, which then triggers heating. As a result of this fault, the room uses excessive energy to maintain comfort.

There were five rooms with similar issues on the same floor and 15 overall within the building. The cause of the fault: the designed air flow specifications were based on maximum occupancy. Issues such as these cause enormous energy waste, and they often go unnoticed for years.

A path forward 

In this post we’ve provided some foundational concepts to consider in how you can better use data to improve both facility performance and availability.

Whether your goal is to improve building performance in support of sustainability transformation or to improve fault detection, the path starts with modernizing the data models that support your facilities. Following a data modernization path will illustrate where the building architecture that provides the data is not meeting expectations.

As a next step, facilities and IT managers can get started by:

  • Performing a basic audit of their buildings and look for options to gather key parameter data outlined above. 
  • Consolidating data from the relevant sources, applying data standardization, and making use of the fault-detection approach outlined above. 
  • Making use of AWS Data Analytics and AWS AI/ML services to perform data analysis and apply machine learning algorithms to identify data anomalies. Amazon uses these services to manage the thousands of world-class facilities that serve our employees, customers, and communities. Learn more about our sustainable building initiatives. 

These steps will help identify energy hot spots and hidden faults in your facilities; facilities managers can then make use of this information to fix the relevant faults and drive facility sustainability. Finally, consider making sustainability data easily accessible to executive teams to help drive discussions and decisions on impactful carbon-abatement initiatives.

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.