Causal ML Scientist - Pricing & Experiments

Amazon Inc.; Omaha (NE); On-site; USD 136,000 - 184,000; Full time

Job summary

Amazon.com Services LLC is seeking a Research Scientist to own causal inference at the intersection of ML and pricing experimentation. You will design, train, and deploy causal ML pipelines for pricing use cases, and define strategies balancing econometric and ML approaches.

The role collaborates with economists and engineers to productionize causal methods, evaluate experiments, and publish methodological proposals.

Qualifications

• PhD, or Master’s degree with 4+ years in quantitative field research
• Experience applying scientific principles to business problems and products
• Experience analyzing both experimental and observational data sets

Responsibilities

• Design, train, evaluate, and deploy end‑to‑end causal ML pipelines for pricing use cases, including CATE estimation models.
• Define identification strategies, model selection criteria, and evaluation standards for econometric vs ML approaches to causal estimation.
• Contribute causal analysis methodology to pricing A/B test post‑analysis and build reusable tooling for non‑ML scientists.
• Assess emerging causal inference methods for applicability to pricing context and author internal methodology proposals.
• Partner with senior economists on identification strategy and collaborate with software and data engineers for production deployment.

Skills

Causal ML

Pricing experiments

A/B testing

CATE estimation

Production ML pipelines

Data analysis

Education

PhD or Master’s with 4+ years in quantitative field research

Tools

R

MATLAB

Python

Java

C++

Job description

Amazon.com Services LLC is seeking a Research Scientist to own causal inference at the intersection of ML and pricing experimentation. You will design, train, and deploy causal ML pipelines for pricing use cases, and define strategies balancing econometric and ML approaches.

The role collaborates with economists and engineers to productionize causal methods, evaluate experiments, and publish methodological proposals.