Economist, Amazon Devices Demand Planning

Are you excited about using econometrics to make multi-million dollar decisions more Science and Data Driven? Are you interested in supporting Consumer Hardware device concepts from innovative idea inception to launch? Do you want to work on a Economics and Data Science team focused on tackling some of the hardest business questions within the Devices business at Amazon and then scaling those Statistics and Econometrics solutions via internal to Amazon tools? Then this could be the role for you!

The Decision Science team owns demand estimates and pricing recommendations of concept devices before customers know they exist. We support analyses on hardware and services ranging from Echo Frames to Kindle Paperwhite to Blink Video Camera subscriptions to the Amazon Smart Plug - all prior to launch. In this role, you will develop science for high visible senior leadership decisions on new devices and services and work with a cross-functional team to apply and scale innovative science broadly.

Key job responsibilities

• Design, estimate, and scale Berry-Levinsohn-Pakes (BLP) random coefficients demand models to quantify consumer heterogeneity, own- and cross-price elasticities, and substitution patterns across large product markets.
• Implement and optimize numerical routines-including GMM estimation, contraction mappings, and simulation-based inversion-to solve structural demand systems at scale in Python.
• Develop and validate instrumental variables strategies to address price endogeneity in differentiated product markets, ensuring unbiased and robust demand parameter estimates.
• Build production-grade pipelines that ingest large-scale observational datasets, estimate consumer preferences, and generate product-level demand forecasts on recurring schedules.
• Collaborate with cross-functional teams including product management, marketing, and operations to translate structural model outputs-such as willingness-to-pay and competitive diversion ratios-into actionable pricing and portfolio strategies.
• Advance the team"s structural modeling capabilities by researching and deploying extensions to classical BLP frameworks (e.g., supply-side estimation, dynamic demand, micro-moments) and documenting approaches in clear technical reports.