About the job
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 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
Qualifications
Minimum
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
Preferred
Knowledge of machine learning concepts and their application to reasoning and problem-solving
Experience applying quantitative analysis to solve business problems and making data-driven business decisions