Amazon is hiring a Manager to lead a science team within Customer Forecasting and Valuation (CFV). CFV owns several of the primary decision metrics Amazon uses to evaluate launches and investments - causal estimates of how customer actions today translate into customer value over the year ahead. These metrics are how Amazon works backwards from the customer at scale: they let thousands of launch decisions a year, across Retail, Ads, Marketing, and Selection, weigh short-term profitability against long-term growth.
We are in the middle of a generational rebuild of how these metrics are produced. Our team is developing transformer-based foundation models of customer behavior, learned directly from billions of behavioral events. They are being built as shared infrastructure: one learned representation of customer behavior that a wide range of measurement and optimization systems across Amazon can be built on top of.
CFV is part of the Customer Behavior Analytics (CBA) organization, which builds the tools used to understand customer behavior and value generation across Amazon"s Retail business.
As a manager in CFV, you will lead Applied Scientists, Economists, and Data Scientists working at the intersection of causal inference, sequence modeling, and experimentation. The work spans methodological invention - making learned representations estimation-aware, closing the loop between experimental ground truth and model training, extrapolating short-horizon observations into year-ahead causal effects - and translation of that work into production systems that move real launch decisions. You will set multi-year research and product agendas in partnership with senior scientists, product owners, and business leaders, and you will work closely with a dedicated engineering team.
The right candidate has deep expertise in ML and causal inference, judgment about when to invent versus reuse, and the appetite to operate in ambiguity. If you want to lead a team shaping how Amazon measures the value of what it does for customers, and how it balances short-term profitability with long-term growth, we should talk.