We are seeking an Applied Scientist II to join Amazon Customer Service's Science team, where you will build AI-based automated customer service solutions using state-of-the-art techniques in retrieval-augmented generation (RAG), agentic AI, and post-training of large language models. You will work at the intersection of research and production, developing intelligent systems that directly impact millions of customers while collaborating with scientists, engineers, and product managers in a fast-paced, innovative environment.

Design, develop, and deploy information retrieval systems and RAG pipelines using embedding models, reranking algorithms, and generative models to improve customer service automation

Conduct post-training of large language models using techniques such as Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Group Relative Policy Optimization (GRPO) to optimize model performance for customer service tasks

Build and curate high-quality datasets for model training and evaluation, ensuring data quality and relevance for customer service applications

Design and implement comprehensive evaluation frameworks, including data curation, metrics development, and methods such as LLM-as-a-judge to assess model performance

Develop AI agents for automated customer service, understanding their advantages and common pitfalls, and implementing solutions that balance automation with customer satisfaction

Independently perform research and development with minimal guidance, staying current with the latest advances in machine learning and AI

Collaborate with cross-functional teams including engineering, product management, and operations to translate research into production systems

Publish findings and contribute to the broader scientific community through papers, patents, and open-source contributions

Monitor and improve deployed models based on real-world performance metrics and customer feedback