senior research scientist Jonathan Toner profile picture
Since joining Amazon Flex, senior research scientist Jonathan Toner has created an entire ecosystem of machine learning models and optimization tools to incentivize Amazon Flex participation.

Jonathan Toner’s hunt for hard questions took him from Antarctica to Amazon

How the former astrobiology professor is charting new territory as a scientist for Amazon Flex.

For as long as he can remember, Jonathan Toner has been drawn to the toughest problems he can find. Where did life originate? What can Earth’s most extreme environments tell us about the planet’s history? Was Mars always the desolate, lifeless place we imagined it to be?

Toner investigated these and other questions as a research assistant professor of Earth and space sciences at the University of Washington (UW), where he also earned a PhD in geophysics. After more than a decade in academia, he joined the Amazon Flex team as a research scientist in 2020. It was an eyebrow-raising move: The two careers have very little overlap in subject matter. But crucially, both require an explorer’s mindset.

Jonathan Toner is seen in Antartica, he is standing on some large rocks wearing a red parka with a mountain range in the background
Jonathan Toner, seen here in Antartica, was a research assistant professor of Earth and space sciences at the University of Washington, where he also earned a PhD in geophysics.

From a young age, Toner was different from his peers. Like other kids, he went to the library to find fun, entertaining reads, but young Jonathan also checked out books on relativity, number theory, and calculus.

“I was pretty curious — maybe a little weird,” he says. “Topics that other people tended to avoid as too difficult, I’d see as a challenge.” When it came to picking a major at the College of New Jersey, the choice was easy: “I’d heard that physics was the hardest, so I did that.”

Making the transition to tech

When grad school beckoned, he decided to combine his passions for science and the outdoors by studying at UW, which is close to the Cascade Range. A few months later, much to his delight, he was conducting field studies at the McMurdo Dry Valleys in Antarctica. It was the first of three expeditions to Antarctica, with the most recent in 2017, funded by NASA and the U.S. National Science Foundation.

I would write an application and say, ‘I’ve got a PhD in geophysics, and I studied planetary science. They’d look at that and be like, ‘Who are you?’
Jonathan Toner

Antarctica is a fertile region for scientific study — particularly the effects of climate change, but also as an analogue for the extreme environments found on Mars or the icy moons of Jupiter or Saturn. In his pursuit of ever-harder questions, Toner moved from physics to geophysics to planetary chemistry to astrobiology. He even investigated the watery origins of life itself.

By 2019, Toner was at the top of his game: a strong publication record and research funding for his ongoing projects at one of the world’s leading institutions for planetary science. But looking into the far future, he didn’t like what he was seeing. He had a strong desire to remain in the Seattle area, but he felt his opportunities to progress in academia were limited, and he had a young family to support, so Toner decided to look for opportunities in the tech industry.

Jonathan Toner is seen here at Don Juan Pond, a shallow hypersaline lake in Antartica
Jonathan Toner, seen here at Don Juan Pond, a shallow hypersaline lake in Antartica, taught himself to build machine learning models and the Python programming language to assist his transition into the tech world.

“I had friends in tech who were doing really well and could live wherever they wanted,” he said. “And I thought to myself, ‘I can do that.’”

He started applying for a few positions, but his situation was unusual, to say the least: “I would write an application and say, ‘I’ve got a PhD in geophysics, and I studied planetary science. They’d look at that and be like, ‘Who are you?’”

This is where Toner’s intellectual tenacity kicked in. He had very little need for machine learning in his field and limited programming experience. So, leveraging his strong academic fundamentals, he taught himself both.

Free ML education resources
New, free offering provides students of any level practical skills and code examples for every stage, from the machine learning problem all the way to deployment.

“I bought a load of machine learning and stats textbooks. I read them. I did the problems. I took about 10 online courses,” he says. “I taught myself to build machine learning models and the Python programming language.” And he did all that in just three months.

And while Toner didn’t have specific experience in the tech industry, he had credentials from other technical fields. In particular, he had developed complex applied models, including thermal and physical diffusion in Martian soils, and thermodynamic models of multicomponent solutions.

“Machine learning is perhaps a step down in complexity from that,” says Toner, “but it’s like trying to gauge the difference in difficulty between playing the violin and the piano.”

That approach worked and, in May of 2020, Toner joined Amazon in the logistics space.

Satisfying two kinds of customers on Amazon Flex

Package delivery to Amazon customers occurs in a variety of ways, including via Amazon Flex. Launched in September 2015, Amazon Flex offers individuals the flexibility to use their own vehicles and set their own schedules while making deliveries as a way of earning extra money. Amazon Flex drivers pick up customer orders from a local Amazon pick-up location and deliver them directly to customers. The Amazon Flex business was built to support Amazon’s growth and meet customer expectations for fast deliveries.

Amazon Flex drivers are our customers too. So, we have this dynamic of multiple customers to satisfy, and that becomes a really intricate science problem. How do you keep everyone happy? It’s a fun problem to think about.
Jonathan Toner

Toner’s overarching goal is to find cost-effective ways to keep Amazon Flex drivers happy and signing up for more blocks, which ensures the service has enough driver capacity to meet projected demand.

“Amazon is customer-obsessed, and you normally think of the customer as the person receiving a delivery. But Amazon Flex drivers are our customers too,” says Toner. “So, we have this dynamic of multiple customers to satisfy, and that becomes a really intricate science problem. How do you keep everyone happy? It’s a fun problem to think about. It occupies all my time.”

As independent contractors, Amazon Flex drivers have the flexibility to accept offers and schedule blocks when it suits them. This means Amazon needs to make sure the program is attractive to drivers, so they feel confident that their time is well-spent with Amazon Flex. This can be through a combination of things, such as block pricing, promotional activity, and desirable delivery windows.

“A lot of our work is around forecasting what Amazon Flex drivers will do, what they want, and ensuring that they have a good experience ,” Toner explains.

The science of forecasting
The story of a decade-plus long journey toward a unified forecasting model.

Amazon Flex has been active in the U.S. since 2017 — and it is growing quickly.

“Given that the number of Flex depots and working drivers on any given week is so large, manual adjustments are impractical,” Toner says. So he is working with Amazon product and business operations teams to create smart, autonomous systems that balance customer needs.

Since joining Amazon Flex, Toner has been promoted to senior research scientist and has created an entire ecosystem of machine learning models and optimization tools. This ecosystem is orchestrated to recommend recruiting actions for Amazon Flex in the US. It considers forecasted delivery demand, predicts capacity contributions from existing drivers and potential new recruits, and predicts how drivers will flow through the onboarding process.

“What intrigues me about this ecosystem of tools is that it is many different models all interacting with each other,” says Toner. “And it’s allowed me to work on so many approaches: Markov chain models powered by logistic regression, recurrent neural networks, dynamic programming to find optimal policies. It definitely keeps me interested.”

Intellectual freedom

Toner also appreciates the latitude he is given to create this smorgasbord of tools.

“Coming from academia, I had some reservations. I was worried about being micromanaged. But I was very pleasantly surprised,” says Toner. “My colleagues are lovely people — so smart and supportive. And, crucially, they allow me freedom to do my thing.”

There's rich science to be done with a company like Amazon that is not available elsewhere. I’ve grown enormously as a scientist because of it.
Jonathan Toner

Right now, Toner’s thing is the ongoing expansion of his suite of models, which for now is focused on the US.

“I want to expand worldwide, and I’ve had interest from Amazon Flex in various countries,” he says.

He is also working on long-lead planning for Amazon Flex, which means modelling driver capacity many years in advance. “This is a very hard question. I mean, where do you even start? To me, that’s a gold mine.”

Career advice
Belinda Zeng, head of applied science and engineering at Amazon Search Science and AI, shares her perspective.

Does Toner have any advice for others in academia considering making the move into the tech industry?

“When you're in academia, it really is like an ivory tower, and going to the corporate world can be viewed with pessimism,” he says. “But I would strongly argue against that. There's rich science to be done with a company like Amazon that is not available elsewhere. I’ve grown enormously as a scientist because of it.”

Toner also counsels against limiting yourself based on what you think you can do:

“Science is really about the interesting questions, right? So, focus on the questions. The methods will come.”

Related content

US, WA, Virtual Contact Center-WA
We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Python is necessary, and experience with SQL and UNIX would be a plus. These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, scientists, and product managers. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement. Roughly 85% of previous cohorts have converted to full time scientist employment at Amazon. If you are interested, please send your CV to our mailing list at econ-internship@amazon.com. About the team The Selling Partner Fees team owns the end-to-end fees experience for two million active third party sellers. We own the fee strategy, fee seller experience, fee accuracy and integrity, fee science and analytics, and we provide scalable technology to monetize all services available to third-party sellers. Within the Science team, our goal is to understand the impact of changing fees on Seller (supply) and Customers (demand) behavior (e.g. price changes, advertising strategy changes, introducing new selection etc.) as well as using this information to optimize our fee structure and maximizing our long term profitability.
US, WA, Seattle
This is a unique opportunity to build technology and science that millions of people will use every day. Are you excited about working on large scale Natural Language Processing (NLP), Machine Learning (ML), and Deep Learning (DL)? We are embarking on a multi-year journey to improve the shopping experience for customers globally. Amazon Search team creates customer-focused search solutions and technologies that makes shopping delightful and effortless for our customers. Our goal is to understand what customers are looking for in whatever language happens to be their choice at the moment and help them find what they need in Amazon's vast catalog of billions of products. As Amazon expands to new geographies, we are faced with the unique challenge of maintaining the bar on Search Quality due to the diversity in user preferences, multilingual search and data scarcity in new locales. We are looking for an applied researcher to work on improving search on Amazon using NLP, ML, and DL technology. As an Applied Scientist, you will lead our efforts in query understanding, semantic matching (e.g. is a drone the same as quadcopter?), relevance ranking (what is a "funny halloween costume"?), language identification (did the customer just switch to their mother tongue?), machine translation (猫の餌を注文する). This is a highly visible role with a huge impact on Amazon customers and business. As part of this role, you will develop high precision, high recall, and low latency solutions for search. Your solutions should work for all languages that Amazon supports and will be used in all Amazon locales world-wide. You will develop scalable science and engineering solutions that work successfully in production. You will work with leaders to develop a strategic vision and long term plans to improve search globally. We are growing our collaborative group of engineers and applied scientists by expanding into new areas. This is a position on Global Search Quality team in Seattle Washington. We are moving fast to change the way Amazon search works. Together with a multi-disciplinary team you will work on building solutions with NLP/ML/DL at its core. Along the way, you’ll learn a ton, have fun and make a positive impact on millions of people. Come and join us as we invent new ways to delight Amazon customers.
US, WA, Seattle
This is a unique opportunity to build technology and science that millions of people will use every day. Are you excited about working on large scale Natural Language Processing (NLP), Machine Learning (ML), and Deep Learning (DL)? We are embarking on a multi-year journey to improve the shopping experience for customers globally. Amazon Search team creates customer-focused search solutions and technologies that makes shopping delightful and effortless for our customers. Our goal is to understand what customers are looking for in whatever language happens to be their choice at the moment and help them find what they need in Amazon's vast catalog of billions of products. As Amazon expands to new geographies, we are faced with the unique challenge of maintaining the bar on Search Quality due to the diversity in user preferences, multilingual search and data scarcity in new locales. We are looking for an applied researcher to work on improving search on Amazon using NLP, ML, and DL technology. As an Applied Scientist, you will lead our efforts in query understanding, semantic matching (e.g. is a drone the same as quadcopter?), relevance ranking (what is a "funny halloween costume"?), language identification (did the customer just switch to their mother tongue?), machine translation (猫の餌を注文する). This is a highly visible role with a huge impact on Amazon customers and business. As part of this role, you will develop high precision, high recall, and low latency solutions for search. Your solutions should work for all languages that Amazon supports and will be used in all Amazon locales world-wide. You will develop scalable science and engineering solutions that work successfully in production. You will work with leaders to develop a strategic vision and long term plans to improve search globally. We are growing our collaborative group of engineers and applied scientists by expanding into new areas. This is a position on Global Search Quality team in Seattle Washington. We are moving fast to change the way Amazon search works. Together with a multi-disciplinary team you will work on building solutions with NLP/ML/DL at its core. Along the way, you’ll learn a ton, have fun and make a positive impact on millions of people. Come and join us as we invent new ways to delight Amazon customers.
US, WA, Seattle
The retail pricing science and research group is a team of scientists and economists who design and implement the analytics powering pricing for Amazon’s on-line retail business. The team uses world-class analytics to make sure that the prices for all of Amazon’s goods and services are aligned with Amazon’s corporate goals. We are seeking an experienced high-energy Economist to help envision, design and build the next generation of retail pricing capabilities. You will work at the intersection of economic theory, statistical inference, and machine learning to design new methods and pricing strategies to deliver game changing value to our customers. Roughly 85% of previous intern cohorts have converted to full time scientist employment at Amazon. If you are interested, please send your CV to our mailing list at econ-internship@amazon.com. Key job responsibilities Amazon’s Pricing Science and Research team is seeking an Economist to help envision, design and build the next generation of pricing capabilities behind Amazon’s on-line retail business. As an economist on our team, you will work at the intersection of economic theory, statistical inference, and machine learning to design new methods and pricing strategies with the potential to deliver game changing value to our customers. This is an opportunity for a high-energy individual to work with our unprecedented retail data to bring cutting edge research into real world applications, and communicate the insights we produce to our leadership. This position is perfect for someone who has a deep and broad analytic background and is passionate about using mathematical modeling and statistical analysis to make a real difference. You should be familiar with modern tools for data science and business analysis. We are particularly interested in candidates with research background in applied microeconomics, econometrics, statistical inference and/or finance. A day in the life Discussions with business partners, as well as product managers and tech leaders to understand the business problem. Brainstorming with other scientists and economists to design the right model for the problem in hand. Present the results and new ideas for existing or forward looking problems to leadership. Deep dive into the data. Modeling and creating working prototypes. Analyze the results and review with partners. Partnering with other scientists for research problems. About the team The retail pricing science and research group is a team of scientists and economists who design and implement the analytics powering pricing for Amazon’s on-line retail business. The team uses world-class analytics to make sure that the prices for all of Amazon’s goods and services are aligned with Amazon’s corporate goals.
US, CA, San Francisco
The retail pricing science and research group is a team of scientists and economists who design and implement the analytics powering pricing for Amazon's on-line retail business. The team uses world-class analytics to make sure that the prices for all of Amazon's goods and services are aligned with Amazon's corporate goals. We are seeking an experienced high-energy Economist to help envision, design and build the next generation of retail pricing capabilities. You will work at the intersection of statistical inference, experimentation design, economic theory and machine learning to design new methods and pricing strategies for assessing pricing innovations. Roughly 85% of previous intern cohorts have converted to full time scientist employment at Amazon. If you are interested, please send your CV to our mailing list at econ-internship@amazon.com. Key job responsibilities Amazon's Pricing Science and Research team is seeking an Economist to help envision, design and build the next generation of pricing capabilities behind Amazon's on-line retail business. As an economist on our team, you will will have the opportunity to work with our unprecedented retail data to bring cutting edge research into real world applications, and communicate the insights we produce to our leadership. This position is perfect for someone who has a deep and broad analytic background and is passionate about using mathematical modeling and statistical analysis to make a real difference. You should be familiar with modern tools for data science and business analysis. We are particularly interested in candidates with research background in experimentation design, applied microeconomics, econometrics, statistical inference and/or finance. A day in the life Discussions with business partners, as well as product managers and tech leaders to understand the business problem. Brainstorming with other scientists and economists to design the right model for the problem in hand. Present the results and new ideas for existing or forward looking problems to leadership. Deep dive into the data. Modeling and creating working prototypes. Analyze the results and review with partners. Partnering with other scientists for research problems. About the team The retail pricing science and research group is a team of scientists and economists who design and implement the analytics powering pricing for Amazon's on-line retail business. The team uses world-class analytics to make sure that the prices for all of Amazon's goods and services are aligned with Amazon's corporate goals.
US, WA, Bellevue
We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Python is necessary, and experience with SQL and UNIX would be a plus. These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, scientists, and product managers. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement. Roughly 85% of interns from previous cohorts have converted to full time economics employment at Amazon. If you are interested, please send your CV to our mailing list at econ-internship@amazon.com.
US
The Amazon Supply Chain Optimization Technology (SCOT) organization is looking for an Intern in Economics to work on exciting and challenging problems related to Amazon's worldwide inventory planning. SCOT provides unique opportunities to both create and see the direct impact of your work on billions of dollars’ worth of inventory, in one of the world’s most advanced supply chains, and at massive scale. We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. We are looking for a PhD candidate with exposure to Program Evaluation/Causal Inference. Knowledge of econometrics and Stata/R/or Python is necessary, and experience with SQL, Hadoop, and Spark would be a plus. These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, scientists, and product managers. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement. Roughly 85% of previous cohorts have converted to full time scientist employment at Amazon. If you are interested, please send your CV to our mailing list at econ-internship@amazon.com.
US, WA, Seattle
The Selling Partner Fees team owns the end-to-end fees experience for two million active third party sellers. We own the fee strategy, fee seller experience, fee accuracy and integrity, fee science and analytics, and we provide scalable technology to monetize all services available to third-party sellers. We are looking for an Intern Economist with excellent coding skills to design and develop rigorous models to assess the causal impact of fees on third party sellers’ behavior and business performance. As a Science Intern, you will have access to large datasets with billions of transactions and will translate ambiguous fee related business problems into rigorous scientific models. You will work on real world problems which will help to inform strategic direction and have the opportunity to make an impact for both Amazon and our Selling Partners.
US, WA, Bellevue
We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. We are looking for a PhD candidate with exposure to Program Evaluation/Causal Inference. Some knowledge of econometrics, as well as basic familiarity with Stata or R is necessary, and experience with SQL, Hadoop, Spark and Python would be a plus. These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, scientists, and product managers. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement. Roughly 85% of previous cohorts have converted to full time scientist employment at Amazon. If you are interested, please send your CV to our mailing list at econ-internship@amazon.com.
US, MA, Boston
Are you inspired by invention? Is problem solving through teamwork in your DNA? Do you like the idea of seeing how your work impacts the bigger picture? Answer yes to any of these and you’ll fit right in here at Amazon Robotics. We are a smart team of doers that work passionately to apply cutting edge advances in robotics and software to solve real-world challenges that will transform our customers’ experiences in ways we can’t even imagine yet. We invent new improvements every day. We are Amazon Robotics and we will give you the tools and support you need to invent with us in ways that are rewarding, fulfilling and fun. Amazon Robotics, a wholly owned subsidiary of Amazon.com, empowers a smarter, faster, more consistent customer experience through automation. Amazon Robotics automates fulfillment center operations using various methods of robotic technology including autonomous mobile robots, sophisticated control software, language perception, power management, computer vision, depth sensing, machine learning, object recognition, and semantic understanding of commands. Amazon Robotics has a dedicated focus on research and development to continuously explore new opportunities to extend its product lines into new areas. AR is seeking uniquely talented and motivated data scientists to join our Global Services and Support (GSS) Tools Team. GSS Tools focuses on improving the supportability of the Amazon Robotics solutions through automation, with the explicit goal of simplifying issue resolution for our global network of Fulfillment Centers. The candidate will work closely with software engineers, Fulfillment Center operation teams, system engineers, and product managers in the development, qualification, documentation, and deployment of new - as well as enhancements to existing - operational models, metrics, and data driven dashboards. As such, this individual must possess the technical aptitude to pick-up new BI tools and programming languages to interface with different data access layers for metric computation, data mining, and data modeling. This role is a 6 month co-op to join AR full time (40 hours/week) from July – December 2023. The Co-op will be responsible for: Diving deep into operational data and metrics to identify and communicate trends used to drive development of new tools for supportability Translating operational metrics into functional requirements for BI-tools, models, and reporting Collaborating with cross functional teams to automate AR problem detection and diagnostics