Applied Scientist, Support Agent Intelligence and Evaluation

We are seeking an Applied Scientist to help enhance and scale our support agent capabilities. You will build and improve models that power advertiser-facing interactions, contribute to our evaluation framework, and work alongside senior scientists and engineers to ship science into production.

Enhance support agent capabilities across the broad suite of Amazon Advertising products — expanding coverage, depth of resolution, and advertiser task completion across Sponsored Products, Sponsored Brands, DSP, AMC, and more

Design and own the evaluation framework for agent quality — including automated LLM-based scoring of answer correctness, confidence calibration, and conversation-level resolution signals

Develop novel metrics that capture whether advertisers actually got the help they needed (beyond surface-level deflection rates)

Build and improve retrieval and generation models that power real-time advertiser interactions under strict latency SLAs

Drive multilingual science — improve non-English resolution rates through cross-lingual retrieval, translation quality modeling, and locale-aware evaluation

Partner with product, engineering, and business teams to productize research and inform roadmap decisions with data