Research Scientist, Selling Partner Experience

Description We’re looking for a Research Scientist to join a team that measures and explains how over 2.4 million sellers and vendors experience selling on Amazon. You’ll apply survey science, psychometrics, and applied statistics to help drive meaningful change at Amazon on behalf of Sellers.

Description We’re looking for a Research Scientist to join a team that measures and explains how over 2.4 million sellers and vendors experience selling on Amazon. You’ll apply survey science, psychometrics, and applied statistics to help drive meaningful change at Amazon on behalf of Sellers. In this role, you’ll work across a variety of research methodologies to optimize our data collection, create scalable analytical approaches, and deep dive the Seller experience to create rigorous, quantitative insights that senior leaders use to set strategy.

• Apply psychometric and survey methodology techniques (e.g., IRT, factor analysis, scale development, single-item indicators) to measure seller experience constructs with scientific rigor
• Contribute to frameworks that link seller attitudinal data to behavioral outcomes and identify high-impact opportunity areas
• Design and execute statistical analyses including regression modeling, significance testing, and driver analysis to identify what matters most to sellers
• Apply observational causal evaluation methods to estimate the effects of policy changes, product launches, and platform interventions on seller experience
• Build and maintain analytical pipelines that transform raw survey data into production-ready metrics, reports, and dashboards
• Analyze open-ended survey responses using text classification, thematic coding, and natural language processing techniques
• Monitor and improve survey response rates, sampling methodology, and data quality
• Productionalize research code: take analyses from prototype to automated, reproducible pipelines that run reliably in production environments
• Communicate findings clearly to technical and non-technical audiences through written reports, data visualizations, and presentations
• Collaborate with cross-functional partners to translate business questions into well-defined research problems and scientific metrics
• Document research methods, assumptions, and limitations transparently to ensure reproducibility

Your day typically starts with the data. You might spend the morning reviewing satisfaction trends, investigating a shift in a key metric, and pulling together an analysis that explains what’s driving it. You’ll regularly meet with external teams to help them understand how a proposed product will affect seller sentiment and what the data says they should prioritize. You’ll also spend time in R or Python building, training, or testing models to improve how we measure and act on sentiment data.

Our team owns the research and measurement infrastructure that tracks satisfaction across all 2.1 million selling partners on Amazon, spanning Seller Central, Next Gen Selling, and Mobile. We sit at the intersection of data and strategy, partnering with teams across product, design, and engineering to advocate for seller experience improvements. This is a high-visibility team where the work is consequential, the stakeholders are senior, and the problems are genuinely hard.

• PhD in a quantitative field, or MS degree and 3+ years of quantitative field research experience
• Experience investigating the feasibility of applying scientific principles and concepts to business problems and products
• Experience with data analysis package (R, SAS, Matlab, etc.)
• Experience using SQL databases to manage and analyze large data sets
• Experience with lab-based user testing, remote testing, iterative prototype testing, survey design, and usage of multiple methods within a study
• Experience applying basic statistical methods (e.g. regression) to difficult business problems
• Experience using data visualization tools
• Experience with survey research methodology and psychometric measurement (e.g., item response theory, factor analysis, scale construction, reliability analysis) as well as single-item indicators