About this role
The Amazon Search team creates customer-focused search solutions and technologies. Whenever a customer visits an Amazon site worldwide and types in a query or browses through product categories, Amazon Product Search services go to work. We design, develop, and deploy high performance, fault-tolerant distributed search systems used by millions of Amazon customers every day. Search Autocomplete and Navigation focuses on helping customers express their shopping intent and navigate search results more effectively. In this role, you will invent universally applicable signals and algorithms to improve suggestion generation, recommendations, and ranking, using LLMs and ML techniques. The improvements you make will help hundreds of millions of customers find the right products faster, from the first keystroke through search result refinement. You will work on problems such as fine-tuning large language models for real-time suggestion generation under strict latency constraints, personalizing recommended content to individual customers, building evaluation frameworks for model selection, and designing data-driven guardrails for LLM-generated content. The work will span the whole development pipeline, including data analysis, evaluation system design, prototyping, A/B testing, and creating production-level systems. Key job responsibilities Your responsibilities include but not limited to: * Analyze the data and metrics resulting from traffic into Amazon's product search service. * Design, build, and deploy effective and innovative ML and LLM solutions to improve search experiences. * Evaluate the proposed solutions via offline benchmark tests as well as online A/B tests in production. * Publish and present your work at internal and external scientific venues in the fields of ML/NLP/IR.