Amazon's Selling Partner Support Science team builds the measurement and AI systems that power how Amazon understands, diagnoses, and eliminates the root causes of support contacts. Our vision is a continuous, science-driven pipeline where LLM-powered classification, causal impact measurement, and multi-modal friction detection work together to identify why Selling Partners experience frictions and quantify which interventions resolve them. Our systems process tens of millions of cases, evaluate hundreds of initiatives annually, and directly inform investment decisions across the Selling Partner Services organization.
We are seeking a world-class Applied Scientist to help define and build the next generation of our LLM and ML systems. You will partner with applied scientists and engineers to design and deploy production-grade NLP pipelines, multi-modal AI frameworks, and scalable classification systems at Amazon's scale, owning your problem space end-to-end, from formulating a scientific approach to shipping a system that 50+ business teams rely on to make better decisions for millions of Selling Partners.
Key job responsibilities
- Use state-of-the-art Machine Learning and Generative AI techniques to create the next generation of the tools that empower Amazon's Selling Partners to succeed.
- Design, develop and deploy highly innovative models to interact with Sellers and delight them with solutions.
- Work closely with teams of scientists and software engineers to drive real-time model implementations and deliver novel and highly impactful features.
- Establish scalable, efficient, automated processes for large scale data analyses, model benchmarking, model validation and model implementation.
- Research and implement novel machine learning and statistical approaches.
- Participate in strategic initiatives to employ the most recent advances in ML in a fast-paced, experimental environment.
About the team
Amazon's Selling Partner Support Science team builds the measurement and AI systems that power how Amazon understands, diagnoses, and eliminates the root causes of support contacts. Our vision is a continuous, science-driven pipeline where LLM-powered classification, causal impact measurement, and multi-modal friction detection work together to identify why Selling Partners experience frictions and quantify which interventions resolve them. Our systems process tens of millions of cases, evaluate hundreds of initiatives annually, and directly inform investment decisions across the Selling Partner Services organization.