Data Scientist, Demand Forecasting

What does it take to build a foundation model that can forecast demand for hundreds of millions of products including ones that have never been sold before

At Amazon our Demand Forecasting team is tackling one of the most ambitious challenges in applied time series research: building large-scale foundation models that generalize across an enormous and diverse catalog of products geographies and business contexts. This is not incremental modeling work. We are redefining whats possible in demand forecasting.

Our team operates at a scale that is unmatched in industry. We run experiments across millions of products simultaneously pushing the boundaries of what foundation models can learn from vast heterogeneous time series data. We are also exploring novel data generation techniques that augment our already unprecedented dataset opening new frontiers in model generalization and forecasting for products with limited or no sales history.

The models you build here will ship to production and directly influence hundreds of millions of dollars in automated inventory decisions every week labor plans for tens of thousands of employees and Amazons financial outlook. Beyond operational impact this team contributes to the broader scientific community and advances the state of the art in time series foundation models.

If you are a scientist who wants to work at the frontier of time series research at a scale no academic lab or startup can match and see your work deployed to real-world impact this is the team for you.

Key job responsibilities
- Design and run rigorous experiments at scale to evaluate and improve foundation model performance across hundreds of millions of products geographies and business verticals
- Lead the end-to-end lifecycle of forecasting models from research and experimentation through production launch including defining success metrics obtaining stakeholder sign-off and managing rollout
- Conduct online and offline labs to measure the real-world impact of forecast improvements beyond accuracy including downstream supply chain inventory and financial outcomes
- Develop and deploy production-grade deep learning and statistical models using Python Scala SQL and related tools
- Perform large-scale exploratory data analysis to uncover patterns identify opportunities and inform model development
- Translate complex research findings into clear insights and recommendations for technical and non-technical stakeholders at all levels
- Contribute to Amazons scientific community and the broader research field through collaboration and publication in top-tier venues

A day in the life
No two days look the same but most will involve some combination of deep technical work cross-functional collaboration and scientific thinking at a scale you wont find anywhere else.

You might start the morning reviewing the results of an experiment running across hundreds of millions of products analyzing whether a new foundation model variant is improving generalization on cold-start items or whether a novel data generation approach is meaningfully shifting forecast quality. Youll dig into the numbers form a hypothesis and design the next iteration.

Later in the day you could be in a stakeholder review walking business and engineering partners through a set of launch metrics explaining not just forecast accuracy but the downstream supply chain and financial impact your model is driving. Getting a model to production at Amazon requires rigor: youll define success criteria run online and offline labs to validate real-world impact and build the case for sign-off across technical and business stakeholders.

Youll write code Python Scala SQL to process and analyze data at a scale most scientists never encounter. Youll collaborate closely with scientists engineers and business teams and contribute to research that has a real chance of being published and advancing the field.

The work is hard the problems are unsolved and the impact is immediate. If you want to do research that ships this is where you do it.

About the team
The Demand Forecasting team sits at the heart of Amazons supply chain building the science that determines what products are available when and at what cost for hundreds of millions of customers around the world. Our mission is to push the frontier of whats possible in large-scale time series forecasting and to deploy that science where it creates real measurable impact.

We are a team of scientists who care deeply about both research rigor and real-world outcomes. We dont just publish we ship. And we dont just ship we measure iterate and raise the bar. Our work spans the full lifecycle: from foundational research and large-scale experimentation to production deployment and downstream impact measurement across supply chain inventory and financial planning.

- 3 years of machine learning statistical modeling data mining and analytics techniques experience
- 3 years of data querying languages (e.g. SQL) scripting languages (e.g. Python) or statistical/mathematical software (e.g. R SAS Matlab etc.) experience
- 3 years of data scientist experience
- Bachelors degree

- Masters degree or PhD
- 2 years of deep learning computer vision human robotic interaction algorithms implementation experience
- Experience processing filtering and presenting large quantities (hundreds of millions/billions of rows) of data
- Experience with forecasting and statistical analysis
- Natural curiosity and desire to learn

Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status disability or other legally protected status.

Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process including support for the interview or onboarding process please visit for more information. If the country/region youre applying in isnt listed please contact your Recruiting Partner.

The base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience qualifications and location. Amazon also offers comprehensive benefits including health insurance (medical dental vision prescription Basic Life & AD&D insurance and option for Supplemental life plans EAP Mental Health Support Medical Advice Line Flexible Spending Accounts Adoption and Surrogacy Reimbursement coverage) 401(k) matching paid time off and parental leave. Learn more about our benefits at WA Bellevue - 136000.00 - 184000.00 USD annually