Data Scientist, Demand Forecasting
About the role
The Demand Forecasting team at Amazon 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 what's possible in demand forecasting.
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 Amazon's scientific community and the broader research field through collaboration and publication in top-tier venues.
Qualifications
1+ years of data querying languages (e.g. SQL), scripting languages (e.g. Python) or statistical/mathematical software (e.g. R, SAS, Matlab, etc.) experience.
2+ years of data/research scientist, statistician or quantitative analyst in an internet-based company with complex and big data sources experience.
Bachelor's degree.