Can you teach a computer to smell? Osmo is trying

The company’s work, supported by the Amazon Alexa Fund, has relevant applications for areas from perfumes to disease detection.

At the age of 12, Alex Wiltschko bought his first perfume, Azzaro pour Homme. He’d read about it in his favorite book — Perfumes: The Guide, by Luca Turin — and was thrilled to find it at a knock-down price at his local TJ Maxx. It would be the first in a large collection.

For as long as he can remember, Wiltschko has been obsessed by scent. “It’s how I’m wired,” he says. His other obsession? Computers. “An interest in perfumes and computers was not the recipe for social success as an adolescent,” he adds.

It was, however, the recipe for a life trajectory that took Wiltschko deep into the neuroscience of olfaction and cutting-edge machine learning. This combination has placed Wiltschko at the forefront of the nascent science of digital olfaction — a.k.a. giving computers a sense of smell.

Wiltschko is now the CEO of Osmo, a Google Research spinout based in Cambridge, Massachusetts. In September 2022, the company hit the ground running with $60 million in initial funding, including an investment from the Amazon Alexa Fund.

In the short term, Osmo aims to unlock a new era of commercial fragrance innovation. Longer term, the company envisions its technologies having the potential to save lives through the development of better insect repellents and even digital diagnostic tools for detecting serious illnesses on a person's breath.

The Principal Odor Map

The keystone to all this is the team’s breakthrough advance: the creation of what it calls the Principal Odor Map (POM).

Before vision could be digitized, a map called RGB was required: It shows how every color is made up of varying proportions of red, green, and blue. Before Osmo was spun out, Wiltschko’s team did something similar — and remarkable — with odor. They used machine learning to map the structure of a molecule directly to how humans perceive the smell of that molecule. In other words, they built a model that can tell you what a molecule smells like just by looking at it. This is the POM.

That was an ‘a-ha!’ moment for us, akin to passing a Turing test for odor. We'd built something with real commercial value that was sufficiently validated to bring into the world.
Jon Hennek

Here’s how they created POM and, crucially, how they proved it worked. They first trained a graph neural network (GNN) on about 5,000 molecules from several flavor and fragrance databases. The smells of all these molecules were well-documented with multiple human-judged odor labels such as beefy, floral, or minty. From this, the model was able to learn connections between molecular structure and odor, without needing any knowledge of what actually happens in the nose or brain of a person sniffing an odor.

That’s great, as far as it goes. The crucial question then was, could POM generalize to predict the smell of molecules it had never seen before, based solely on their molecular structure? And could it do that as well as trained human raters, which is the gold standard for odor characterization? To find out, the team took a diverse set of more than 400 odor molecules previously unseen by POM and had the model blindly predict their characteristics. Then a panel of trained human raters sniffed and labeled those same odors.

When the Osmo team compared the results, they were delighted. Not only had the model successfully predicted the odor of these unseen molecules as well as trained humans, but its predicted odor profiles were closer to the average results of the panel than any of the individual panelists themselves.

“That was an ‘a-ha!’ moment for us, akin to passing a Turing test for odor,” says Jon Hennek, chief product officer at Osmo. “We'd built something with real commercial value that was sufficiently validated to bring into the world.”

Islands of odor

POM is not a map in the typical sense, but it can nevertheless be compared to the RGB map. Pick two points at random on a two-dimensional color map. The closer those two points are to each other, the more similar the color. The same is true for odors in POM, though this map exists in a mind-bending 256 dimensions. All of the tulip-smelling molecules are close to each other, for example. Ditto for the brandy-smelling molecules.

“Zooming out a little, all the flowers are next to each other. There's a whole floral Pangaea in this odor map! We didn't tell it to do that,” says Wiltschko. This sort of grouping is also true for woods, bakery-type smells, alcoholic smells, you name it. Our brain seems to organize smells in nested hierarchies, says Wiltschko, so the rose odor is inside the rose category, inside the flowers category, inside the plants category, inside the pleasant category.

“The fact that we were able to observe this in the POM without telling it is astounding,” he says.

On the left is a color map (the CIE 1931 color space chromaticity diagram), similar colors lie near each other. On the right is Osmo’s Principal Odor Map, individual molecules (grey points) are found nearer to each other if they are predicted to smell similar.
In this color map (the CIE 1931 color space chromaticity diagram), similar colors lie near each other. Likewise, in Osmo’s Principal Odor Map, individual molecules (grey points) are found nearer to each other if they are predicted to smell similar.
Courtesy of Osmo

While Wiltschko has bold ideas for the future of Osmo’s technology, the first order of business is putting the company on a solid commercial footing. For now, Osmo is concentrating on developing new ingredients for the global fragrance category.

The Osmo team is using POM to explore the world of odor molecules — several billion of them — and homing in on molecules that POM predicts to have an interesting and strong olfactory character.

“We're much better at that, I believe, than anybody else in the world,” says Hennek. “Because rather than start with rules of thumb and chemical intuition, we are starting with an odor prediction for every molecule we could possibly synthesize. It lets us find molecules that a chemist might never have considered.”

The team is working with advisors, including Christophe Laudamiel, a French master perfumer, and potential customers include fragrance houses and packaged goods companies.

More from Alexa Fund
Alexa Fund company’s assisted reality tech could unlock speech for hundreds of millions of people who struggle to communicate.

“We've had repeated feedback that our ingredients have the potential to be very successful, commercially,” says Wiltschko. “That smells like product/market fit.” The principal idea is to license those molecules to fragrance houses.

It’s a timely endeavor. The global fragrance category is valued at more than $10 billion and growing steadily. But some traditional ingredients, such as sandalwood oils, can result in over-harvesting or other ecological harm, while the characteristics of other ingredients increasingly fall short as the demand grows for safer, more biodegradable products.

With POM, Osmo is paving the way for palettes of safe, synthetic fragrances that recreate natural odors using environmentally friendly and easily synthesized molecules. To that end Osmo is looking at combinations of just a handful of atoms: carbon, hydrogen, oxygen, nitrogen, phosphorus, and sulfur.

“Then we bring them into our lab for a process akin to a drug discovery pipeline,” says Hennek. “We are working towards regulatory approval of those molecules.”

Rise of the graph neural networks

All of this has only become possible in the last six years or so. The core insight that started this scientific project, says Wiltschko, was that machine learning was “getting really good at molecules,” thanks to the recent rise of GNNs.

Related content
Dual embeddings of each node, as both source and target, and a novel loss function enable 30% to 160% improvements over predecessors.

Previously, machine learning approaches primarily converted inputs — images or data arrays, say — into rectangles or data grids to process them. Molecules didn’t fit this mold: a molecule might be two atoms, or it might be 20 atoms, with wildly different structure and connectivity. They are simply not reducible to rectangles or grids.

Instead, the atoms in a molecule can be considered as nodes, and the chemical bonds between them as edges, forming a graph structure. This representation allows GNNs to model and process molecular data.

“Some of this technology was developed by friends of mine at Google. So, it was a fantastic, fertile ground to start exploring this idea,” says Wiltschko.

This ongoing exploration is creating some exciting possibilities. Wiltschko reasoned that, just as the sun has shone on Earth since before life began, resulting in many creatures evolving similar visual apparatuses, the composition of the Earth’s atmosphere has been broadly stable over evolutionary time. So could POM also be used to understand the olfactory responses of other species, even those separated from humans by millions of years of evolution?

Life-saving potential

Take mosquitos. Could POM be used to work out what odors repel these disease-carrying insects?

To find out, they augmented POM with additional data sources. The first was a long-forgotten U.S. government report, published in the 1940s, that featured the results of testing 19,000 compounds for their mosquito repellency. The second was information provided by TropIQ, a Dutch company that develops malaria-control technology. The augmented model was soon able to predict entirely new molecules with repellency at least as powerful as DEET, the active ingredient in the most effective mosquito repellents.

osmo image 2.png
Osmo digitized mosquito-repellency data for 19,000 compounds reported on by the United States Department of Agriculture and used that to refine its model (left). The team then predicted candidate molecules that would be most repellent to mosquitos, produced the most viable options, tested them on real mosquitos, and fed those results back into the model to further refine it.
Courtesy of Osmo

The development of cheaper, more effective, and safer insect repellents could have a huge impact on global health. Wiltschko has nothing to announce yet, but says this research is ongoing in collaboration with the Bill & Melinda Gates Foundation.

Applying POM to mosquitos is also a proof of concept, says Hennek. “We can picture applying our product not just to what mosquitoes don’t like, but to what roaches don’t like. Or any number of agricultural pests.”

Capturing smell forever

Looking further down the road, Wiltschko’s vision is to digitize our sense of smell. The idea is not as far-fetched as it sounds. Consider several hundred years ago. The idea that a visual moment — the fleeting expression on your child’s face or an orchard of apple trees in blossom — could be instantly captured and made available forever more in perfect color would have been nothing short of magical thinking.

By the 1820s came the first photography, and with it, the first steps towards human mastery of the world of light. Today, it feels like a fundamental right to freeze those visual memories and hold on to them forever. And the same goes for the auditory world.

“We know what’s required to digitize a human sense,” says Wiltschko. “And we don't have to wait for any of the inventions that vision did — particularly integrated circuits.”

Indeed, with modern computing power and the harnessing of machine learning, Wiltschko reckons computers will have a “sense of smell” within a decade or two. Three stages are required: “reading” smell, understanding it, and “writing” it. Osmo wants to understand, and ultimately curate a wide palette of safe, synthetic molecules that can recreate the entire human smellscape. The reading (sensing) of odorous molecules currently requires bulky and expensive lab equipment, such as a gas chromatography mass spectrometer, while the writing (producing) of smells on demand remains science fiction at the consumer level, says Wiltschko, for now.

A window to the inside

Sensing and understanding odor at a high level may be sufficient to herald powerful health applications, says Wiltschko. For example, it is well established that serious illnesses, including some cancers, can be detected through their effect on your breath. Being able to take a snapshot of that odor profile — an “Osmograph”, in Wiltschko’s words – could reveal a great deal about what’s going on inside our bodies.

“We don't know if that technology will ultimately have a transformative effect on healthcare, but I am betting that it will,” he says.

Related content
ARA recipient Marinka Zitnik is focused on how machine learning can enable accurate diagnoses and the development of new treatments and therapies.

It’s very important to Wiltschko that, down the line, Osmo grows to develop clinical diagnostics applications. “That's the North Star for me, and it's very important that we get there. But the sheer cost and the talent that's required is rare and expensive,” he says. “So, it can’t be the first beach that we storm.”

As Osmo grows, it will be looking for similarly passionate people to push the mission forward. “We've been finding that there are people out there who are secret scent lovers, who secretly aspire to work in the field of machine olfaction,” says Wiltschko. “Just to put it out there: there's one place to do this, and it's Osmo.”

Talking to Wiltschko and those inspired to work alongside him, it is clear to see that Osmo is the culmination of his lifelong passions. For him, it’s emotional. “Once you smell a thing, you cannot stop the feelings that you get from it. There's a very fundamental feeling and emotional component,” he says, “and I think that’s beautiful.”

Research areas

Related content

US, WA, Seattle
Amazon's eCommerce Foundation (eCF) organization provides the core technologies that drive and power Amazon's Stores, Digital, and Other (SDO) businesses. Millions of customer page views and orders per day are enabled by the systems eCF builds from the ground up. CloudTune, within eCF, empowers growth and business agility needs by automatically and efficiently managing AWS capacity and business processes needed to safely meet Amazon's customer demand. CloudTune serves its primary customers, internal software teams, through forecast-driven automation of cost controllership, capacity management, and scaling. We predict expected load, and drive procurement and allocation of AWS capacity for new product launches and high-velocity events like Prime Day and Cyber Monday. CloudTune is looking for a Data Scientist to join our forecasting and optimization team. The team develops sophisticated algorithms that combine machine learning-based demand forecasting with mathematical optimization to solve large-scale capacity planning problems under uncertainty. We work with massive datasets — spanning thousands of availability zone and instance family combinations across global regions — to determine optimal resource allocation strategies that balance infrastructure holding costs against service availability requirements. These models directly inform multi-million dollar capacity investment decisions and drive automated procurement, retention, and release policies across Amazon's compute infrastructure. As a Data Scientist in CloudTune, you will work with other scientists, software engineers, data engineers, and product managers on a variety of important research problems in the areas of stochastic optimization, time series modeling, and operations research. You will work on statistical problems with a high level of ambiguity. You will analyze and process large amounts of data, develop new algorithms and improve existing approaches based on statistical models, machine learning algorithms and big data solutions to automatically scale Amazon’s compute infrastructure, optimizing the balance between availability risk and cost efficiency for all of Amazon businesses. Key job responsibilities - Process and analyze large data sets, mining additional data sources as needed - Build statistical models and drive scalable solutions for multi-year capacity demand forecasting horizons - Create, enhance, and maintain technical documentation, and present to other scientists and business leaders - Process and analyze large-scale operational data to identify patterns and inform model development - Create, enhance, and maintain technical documentation, and present research findings to scientists, engineering teams, and senior leadership
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, WA, Redmond
At Amazon, we’re inventing on behalf of customers, and with Amazon Leo, we’re redefining what global connectivity looks like. Our mission is to deliver fast, affordable broadband to unserved and underserved communities around the world through a constellation of low Earth orbit (LEO) satellites. Every system we build helps connect people to education, healthcare, opportunity, and each other. As a Data Scientist, you will be responsible for developing advanced analytics and machine learning solutions for user terminals. You will develop predictive models to proactively identify possible user terminal failures in the field. You will work in a collaborative environment with a multi-disciplinary team, including constellation, RF, antenna, silicon, algorithm, and software engineers. Key job responsibilities As a Data Scientist, you will develop analytic tools for a team developing current and future user terminals. Your responsibilities include: • Develop statistical and analytical tool to enable the regression decision from on-orbit and lab measurement of user terminals • Publish documents and create compelling visualizations and presentations to communicate insights to stakeholders • Create and manage datasets for continued pre-training and supervised fine-tuning of LLMs • Develop scalable visualizations for analysis of user terminal performance • Work closely with constellation, RF, antenna, silicon, algorithm, and software engineers to root-cause the failures using data as the primary tool • Drive consensus on metrics and analysis approaches to support product development strategy 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. A day in the life As a Data Scientist in the LEO Customer Terminal Team, you will work daily with satellite constellation, algorithm, RF, antenna, silicon, hardware, and software teams in a collaborative environment. Your focus will be using data as an intelligence source to enable design decisions for the team. About the team The LEO Customer Terminal team is responsible for developing both outdoor and indoor devices that enable customers to access internet service via the LEO satellite network. We own the entire process from early prototypes through mass production, including requirements documentation, architecture definition, hardware development, algorithm development, and all integration and verification testing.
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.
US, WA, Redmond
Amazon Leo is building a constellation of thousands of low Earth orbit satellites. It will bring fast, reliable internet to customers beyond the reach of existing networks. On the Guidance, Navigation and Control (GNC) team, you will design the algorithms, simulations and onboard autonomy that keep every satellite precisely pointed and stable. Your work lets the payload serve customers on the ground, and it keeps the fleet flying safely. This is satellite GNC at constellation scale. The constellation is launching and growing today, so you will see your work go from concept to orbit, and then fly on many satellites. In this role, you will: - Take your GNC algorithms from concept to orbit, and stay with them through integration, test and on-orbit operations. - Write the production C++ flight code for your own algorithms. The code that flies is the code you write. - Solve hard problems in precise pointing, payload cueing and fleet autonomy. - Work across design, simulation, test and flight operations, not a narrow slice of the lifecycle. **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 - Design and analyze algorithms for state estimation, attitude determination and control, precise pointing and payload cueing against demanding performance requirements. - Implement these algorithms in production C++ flight software. Our GNC engineers own their algorithms all the way into flight, and partner with our embedded software engineers to integrate and test them. - Write concepts of operations for each phase of a satellite's life, from launch and orbit raising to service and deorbit, including failures and recovery. Balance what the payload needs against momentum, power, thermal and ground-contact limits. - Develop momentum management strategies with reaction wheels and magnetic torquers. Help select, size and place the GNC sensors and actuators for future satellites, and design the algorithms that use them. These include star trackers, magnetometers, sun sensors, IMUs and GNSS receivers. - Develop onboard autonomy, including Fault Detection, Isolation and Recovery (FDIR), so that the fleet operates safely at scale with minimal ground intervention. - Build and validate satellite and constellation models and simulations at several levels of fidelity, including 6-DOF simulation and Monte Carlo analysis. Verify closed-loop performance in hardware-in-the-loop (HITL) tests. - Support component environmental tests, functional and performance checkout, and subsystem and satellite integration in our labs. - Analyze telemetry from the whole fleet. Build the metrics, dashboards and tools that track pointing performance and payload operations time as the constellation grows, and use them to improve the fleet. - Operate the GNC system on orbit and take part in the team's on-call rotation. Review fleet data, support maneuvers, and resolve anomalies when on-orbit behavior differs from the ground model. - Review designs and code with the team, and document your algorithms, analyses and results clearly. A day in the life This role covers a wide range of problems across the spacecraft and the network. You will derive and prototype estimation and control algorithms, and then turn them into production flight code. You will prove them in 6-DOF and Monte Carlo simulation and in hardware-in-the-loop tests in the lab. You will support satellite integration. When a satellite does not behave as the ground model predicted, you will dig into fleet telemetry, find the cause and drive the fix. You will own each problem end to end, with the focus to go deep on it. GNC is at the center of safe flight, so you will work across the whole program. The payload, power, thermal and operations teams all depend on GNC, and you will balance their needs against the pointing and momentum budgets. You will partner closely with avionics, flight software and embedded software engineers to make your algorithms run reliably on the spacecraft. You will help the mechanical teams shape the next generation of satellite hardware, from reaction wheels to star trackers. As satellites move from design through manufacturing into orbit, you will work with systems engineering and Assembly, Integration and Test. The problems are hard: tight pointing requirements, a large constellation to keep flying safely, and the chance to invent capabilities that do not exist yet. Constant work with other teams makes this a place where you keep learning and growing. About the team You will join the Satellite Attitude Determination and Control team. We own GNC for our satellites end to end: algorithm design, flight software, lab integration, and flight operations of our own satellites on orbit. Our engineers bring deep experience from many satellite programs and other flight vehicles, with real strength in both our mission and the core GNC disciplines. We design, prototype, test, iterate and learn together. Because GNC is central to safe flight, we drive the concepts of operations and many of the system-level analyses on the program. We also have a lot of freedom. We trust our engineers to choose their own tools and approaches for the problems they face, and to own the results. If you want the autonomy to solve hard problems your way, with a team of strong engineers, you will feel at home here.
US, WA, Redmond
Amazon Leo is building a constellation of thousands of low Earth orbit satellites. It will bring fast, reliable internet to customers beyond the reach of existing networks. On the Guidance, Navigation and Control (GNC) team, you will design the algorithms, simulations and onboard autonomy that keep every satellite precisely pointed and stable. Your work lets the payload serve customers on the ground, and it keeps the fleet flying safely. This is satellite GNC at constellation scale. The constellation is launching and growing today, so you will see your work go from concept to orbit, and then fly on many satellites. In this role, you will: - Take your GNC algorithms from concept to orbit, and stay with them through integration, test and on-orbit operations. - Write the production C++ flight code for your own algorithms. The code that flies is the code you write. - Solve hard problems in precise pointing, payload cueing and fleet autonomy. - Work across design, simulation, test and flight operations, not a narrow slice of the lifecycle. **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 - Design and analyze algorithms for state estimation, attitude determination and control, precise pointing and payload cueing against demanding performance requirements. - Implement these algorithms in production C++ flight software. Our GNC engineers own their algorithms all the way into flight, and partner with our embedded software engineers to integrate and test them. - Write concepts of operations for each phase of a satellite's life, from launch and orbit raising to service and deorbit, including failures and recovery. Balance what the payload needs against momentum, power, thermal and ground-contact limits. - Develop momentum management strategies with reaction wheels and magnetic torquers. Help select, size and place the GNC sensors and actuators for future satellites, and design the algorithms that use them. These include star trackers, magnetometers, sun sensors, IMUs and GNSS receivers. - Develop onboard autonomy, including Fault Detection, Isolation and Recovery (FDIR), so that the fleet operates safely at scale with minimal ground intervention. - Build and validate satellite and constellation models and simulations at several levels of fidelity, including 6-DOF simulation and Monte Carlo analysis. Verify closed-loop performance in hardware-in-the-loop (HITL) tests. - Support component environmental tests, functional and performance checkout, and subsystem and satellite integration in our labs. - Analyze telemetry from the whole fleet. Build the metrics, dashboards and tools that track pointing performance and payload operations time as the constellation grows, and use them to improve the fleet. - Operate the GNC system on orbit and take part in the team's on-call rotation. Review fleet data, support maneuvers, and resolve anomalies when on-orbit behavior differs from the ground model. - Review designs and code with the team, and document your algorithms, analyses and results clearly. A day in the life This role covers a wide range of problems across the spacecraft and the network. You will derive and prototype estimation and control algorithms, and then turn them into production flight code. You will prove them in 6-DOF and Monte Carlo simulation and in hardware-in-the-loop tests in the lab. You will support satellite integration. When a satellite does not behave as the ground model predicted, you will dig into fleet telemetry, find the cause and drive the fix. You will own each problem end to end, with the focus to go deep on it. GNC is at the center of safe flight, so you will work across the whole program. The payload, power, thermal and operations teams all depend on GNC, and you will balance their needs against the pointing and momentum budgets. You will partner closely with avionics, flight software and embedded software engineers to make your algorithms run reliably on the spacecraft. You will help the mechanical teams shape the next generation of satellite hardware, from reaction wheels to star trackers. As satellites move from design through manufacturing into orbit, you will work with systems engineering and Assembly, Integration and Test. The problems are hard: tight pointing requirements, a large constellation to keep flying safely, and the chance to invent capabilities that do not exist yet. Constant work with other teams makes this a place where you keep learning and growing. About the team You will join the Satellite Attitude Determination and Control team. We own GNC for our satellites end to end: algorithm design, flight software, lab integration, and flight operations of our own satellites on orbit. Our engineers bring deep experience from many satellite programs and other flight vehicles, with real strength in both our mission and the core GNC disciplines. We design, prototype, test, iterate and learn together. Because GNC is central to safe flight, we drive the concepts of operations and many of the system-level analyses on the program. We also have a lot of freedom. We trust our engineers to choose their own tools and approaches for the problems they face, and to own the results. If you want the autonomy to solve hard problems your way, with a team of strong engineers, you will feel at home here.
US, WA, Seattle
Do you want to make AI provably correct for chip design and verification? We're hiring an Applied Scientist to combine large language models with formal methods such as Lean 4 and turn AI from a helpful assistant into a trusted engineering tool for silicon. Our team builds the formal verification methods behind custom silicon at Amazon scale. As AI agents take on more of chip design and verification, we need people who can make sure their output is checkable, sound and grounded in mathematics. You will research and build systems where LLMs work alongside interactive theorem provers, SMT solvers and model checkers. Engineers write the specifications. AI refines them against RTL, generates proof steps and closes proofs at machine speed. Every result is checked by a formal kernel, not trusted on faith. Work at the frontier of AI reasoning, theorem proving and hardware verification Ship solutions that directly affect real chips running in AWS data centers Publish and help shape how the industry formalizes AI use in hardware engineering Key job responsibilities Design and build LLM-driven systems for formal verification and design tasks, including proof generation, invariant and lemma discovery, spec-to-RTL refinement, and counterexample analysis Develop frameworks in Lean 4 (and related tools such as SMT solvers, model checkers and commercial FV engines) that formally check AI-generated artifacts, so they are correct by construction rather than just plausible Formalize hardware semantics, ISAs and microarchitectural properties in Lean 4 to create machine-checkable foundations for AI agents to reason over Track and evaluate state-of-the-art AI work (LLM agents, autoformalization, neural theorem proving, reinforcement learning from proof feedback) and turn promising research into production tools Build benchmarks and evaluation methods that measure AI soundness, proof success rate and engineering impact on real designs Partner with FV and design engineers to find the highest-leverage problems and deploy solutions into active chip programs Publish research, file patents and represent Amazon in the formal methods and AI communities Mentor engineers and scientists on applying formal AI methods
US, CA, Pasadena
We are seeking Applied Scientists to join Amazon. In this role, you will develop and deploy the science of safe autonomy on highly dynamic robots, advancing the frontier through both foundational research and realization on hardware. You will contribute to achieving safe autonomy across three key areas: control barrier function (CBF) theory for robust and performant safety on hardware; safe reinforcement learning for agile whole-body control; and layered safety filters that interface with learning, perception, and semantic reasoning systems. You will validate your work experimentally on state-of-the-art robotic platforms — removing bottlenecks to deployment and enabling robots to safely operate around humans. You will work with the inventor of CBFs, as well as top scientists and engineers at Amazon developing the next generation of safe autonomy. Key job responsibilities -Advance the science of safe autonomy from formal foundations to the integration with learning and perception to validation on hardware — with particular emphasis on methods that bridge these domains. -Test and validate hardware, with a focus on next generation robotic systems. Including locomotion, manipulation and loco-manipulation. -Leverage the deployments on hardware to validate the underlying science, identifying gaps between theory and practice that drive the next cycle of research. hardware to validate the underlying science, identifying gaps between theory and practice that drive the next cycle of research. -Publish research at top-tier robotics, control, and ML venues, and contribute to Amazon’s scientific reputation in advanced robotics. -Collaborate with SAF Lab and Amazon production teams to move research into robots deployed at Amazon scale. A day in the life Amazon offers a full range of benefits that support you and eligible family members, including domestic partners and their children. Benefits can vary by location, the number of regularly scheduled hours you work, length of employment, and job status such as seasonal or temporary employment. The benefits that generally apply to regular, full-time employees include: -Medical, Dental, and Vision Coverage -Maternity and Parental Leave Options -Paid Time Off (PTO) -401(k) Plan If you are not sure that every qualification on the list above describes you exactly, we’d still love to hear from you! At Amazon, we value people with unique backgrounds, experiences, and skillsets. If you’re passionate about this role and want to make an impact on a global scale, please apply! About the team The Safe Autonomy Frontiers (SAF) Lab is the first industry research lab dedicated to safe autonomy, founded by the inventor of control barrier functions. We are developing a universal safety layer for the next generation of robotic systems: mobile robots, manipulators, quadrupeds, and humanoids. Here you will advance performant safety for highly dynamic robots — CBF theory integrated with perception and learning, evaluated on next-generation platforms — and your work will underpin robots operating alongside people at Amazon’s unprecedented scale.
US, MA, North Reading
Robotics Applied Scientist II Intern/Co-op (2027) Are you passionate about robotics and research? Do you want to solve real customer problems through innovative technology? Do you enjoy working on scalable research and projects in a collaborative team environment? Do you want to see your science solutions directly impact millions of customers worldwide? We’re looking for current PhD students with a passion for robotic research and applications to join us in 2027 as Robotics Applied Scientist II Interns/Co-ops to shape the future of robotics and transform automation at Amazon’s scale. By applying to this role, you will be considered for Robotics Applied Scientist II Intern/Co-op (2027) opportunities across various Robotics teams at Amazon with different robotics research focus. Internship positions are available for multiple locations, durations (3 to 6+ months), and year-round start dates (winter, spring, summer, fall). Join us at the forefront of Applied Science, where your contributions will shape the future of Robotics! Key job responsibilities As a Robotics Applied Scientist II Intern/Co-op, you will work alongside global experts to advance the state of the art in robotics and artificial intelligence, tackling innovative problems that bridge the gap between research and real-world robotics implementation to innovate and build solutions on behalf of our customers. We are particularly interested in students with specialization and expertise in one or more of the following research areas: - Robotics - Artificial Intelligence - Robotics Manipulation (e.g., robot arm, grasping, dexterous manipulation, end of arm tools/end effector) - Autonomous Mobile Robots - Mobile Manipulation - Multi-Robot Coordination - Autonomous Navigation - Locomotion - Motion/Path Planning - Controls - Perception - Sensing - Robot Learning - Machine Learning - Computer Vision - Large Language Models (LLM), Vision-Language-Action Models (VLA), Vision-Language-Models (VLM) - World Models - Human-Robot Interaction - Robotics Simulation - Optimization - And related! Key responsibilities may include: - Develop novel, scalable algorithms and/or modeling techniques that advance the state-of-the-art in science areas such as robotics, artificial intelligence, or related - Tackle challenging, innovative research problems within robotics, artificial intelligence, or related that bridge the gap between theoretical advancement and practical robotics implementation - Collaborate with cross-functional teams to solve complex problems, and to communicate research findings clearly, leveraging your expertise in robotics, artificial intelligence, or related - Demonstrate the ability to work independently, thrive in a fast-paced, ever-changing environment - Leverage AI-powered tools where applicable to accelerate research, experimentation, and prototyping. - Critically review and validate outputs from AI tools and automated systems. About the team Explore Robotics Teams at Amazon At Amazon, robotics is where innovative research meets real-world deployment. There are many different specialized robotics teams, including the few highlighted below. Learn more about Robotics at Amazon here: https://www.amazon.science/research-areas/robotics Fulfillment Technologies and Robotics We build dynamic partnerships between people and intelligent machines. This intricate collaboration helps Amazon fulfill orders with unmatched accuracy. Working in symphony with our robotic technology, you’ll have the opportunity to extend your technical capabilities by working alongside some of the industry’s most advanced technologies. This includes our fleet of autonomous mobile robots, sophisticated control software, and technologies like language perception, machine learning, object recognition, and semantic understanding of commands. These technologies help us deliver an ever-improving customer and employee experience, as well as improve the safety of our facilities. Amazon Robotics Amazon Robotics is at the epicenter of robotics innovation. We design, test, and build mobile robots and mechatronic systems. Our offices, labs, test floors, and factories are close together, which means we can design the hardware, write the code, test, build, and watch it all come to life. Our areas of focus include advancements in autonomous mobility, AI, robotic management software, and much more. Fauna Fauna is focused on building capable, safe, and genuinely delightful robots for everyday life. Fauna’s goal is simple: make robots people actually want to live and interact with everyday. Fauna develops tightly integrated hardware and software systems that make it faster, safer, and more intuitive to create real-world robotic products. Fauna’s work spans the full stack: mechanical design, control systems, dynamic modeling, and intelligent software. The focus is not just functionality, but overall experience. Amazon Fulfillment Technologies Amazon Fulfillment Technologies develops tech solutions that create network optimizations for all Amazon sites worldwide. We own network infrastructure and devices in all buildings and labor planning and scheduling technology for fulfillment centers in North America and Europe.
US, WA, Seattle
MULTIPLE POSITIONS AVAILABLE Employer: AMAZON.COM SERVICES LLC Offered Position: Applied Scientist III Job Location: Seattle, Washington Job Number: AMZ10037670 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, and run and analyze experiments in a production environment. Identify new opportunities for research in order to meet business goals. Research and implement novel ML and statistical approaches to add value to the business. Mentor junior engineers and scientists. Position Requirements: Master’s degree or foreign equivalent degree in Computer Science, Machine Learning, Engineering, or a related field and two years of research or work experience in the job offered, or as a Research Scientist, Research Assistant, Software Engineer, or a related occupation. Employer will accept a Bachelor’s degree or foreign equivalent degree in Computer Science, Machine Learning, Engineering, or a related field and five years of progressive post-baccalaureate research or work experience in the job offered or a related occupation as equivalent to the Master’s degree and two years of research or work experience. Must have one year of research or work experience in the following skill(s): (1) programming in Java, C++, Python, or equivalent programming language; and (2) conducting the analysis and development of various supervised and unsupervised machine learning models for moderately complex projects in business, science, or engineering. Amazon.com is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation. 40 hours / week, 8:00am-5:00pm, Salary Range $167,100/year to $226,100/year. Amazon is a total compensation company. Dependent on the position offered, equity, sign-on payments, and other forms of compensation may be provided as part of a total compensation package, in addition to a full range of medical, financial, and/or other benefits. For more information, visit: https://www.aboutamazon.com/workplace/employee-benefits. #0000