About the job
We are seeking an experienced Data Scientist to drive scientific tooling supporting how Amazon's business customers interact with LTPF forecasts and plans. As a science leader within the LTPF, you will be responsible for building to the multi-year roadmap for customer engagement, ensuring that business stakeholders across Amazon can seamlessly access, understand, and act upon our forecasting outputs. In this role, you will manage the lifecycle of complex, cross-functional programs that transform how Operations, Stores, and Finance teams leverage LTPF insights for strategic decision-making. You will work with scientists, economists, engineers, and business customers to architect the customer interaction experience, including viewing capabilities, auditing tools, what-if analysis frameworks, and forecast intervention workflows.
Responsibilities
- You will develop causal inference models, automated explainability frameworks, and variance bridging methodologies that translate LTPF's forecasts and plans into actionable business intelligence.
- Your work will enable leadership to understand why forecasts and actuals diverge, what is driving demand shifts, and how strategic decisions propagate through the planning ecosystem.
- You will build automated Plan-vs-Actual and Actual-vs-Actual variance decomposition models that quantify the contribution of individual demand drivers to observed gaps across revenue, price, units, inventory, and capacity metrics at multiple granularities to serve audiences from working-level analysts to VP-level planning reviews cycles.
- You will build and maintain a causal model library with standardized hypothesis generation and validation pipelines, applying techniques from causal inference, time-series econometrics, and Bayesian methods. Each model will include calibrated confidence scoring and reusable components that scale across worldwide marketplaces.
- You will develop GenAI-powered narrative generation capabilities that synthesize quantitative variance outputs into human-readable performance summaries and design automated hypothesis ranking to determine which demand drivers are most responsible for observed forecast error.
Qualifications
Minimum
- 2+ years of data scientist 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 machine learning/statistical modeling data analysis tools and techniques, and parameters that affect their performance experience
- 1+ years of guiding and coaching a group of researchers experience
- 1+ years of working with or evaluating AI systems experience
- 1+ years of creating or contributing to mathematical textbooks, research papers, or educational content experience
- Master's degree in Science, Technology, Engineering, or Mathematics (STEM), or experience working in Science, Technology, Engineering, or Mathematics (STEM)
- Experience applying theoretical models in an applied environment
Preferred
- Ph.D. in Science, Technology, Engineering, or Mathematics (STEM)
- Knowledge of machine learning concepts and their application to reasoning and problem-solving
- Experience in Python, Perl, or another scripting language
- Experience in defining and creating benchmarks for assessing GenAI model performance
- Experience effectively communicating complex concepts through written and verbal communication