Amazon Web Services (AWS) is looking for a Principal Applied Scientist to join the Amazon Q team. Q is AWS’s enterprise generative AI assistant that helps users answer questions, summarize documents, generate content, take actions, and automate workflows using information across enterprise systems. As a key member of this team, you will lead research and development efforts in generative AI and Agentic AI to enable intelligent agents that perform complex reasoning, automate multi-step workflows, and make enterprise users significantly more productive.
You’ll work on building and optimizing multi-modal foundation models, training and fine-tuning state-of-the-art LLMs, and architecting systems that scale efficiently across domains. This role blends science leadership, hands-on innovation, and deep collaboration with engineering teams to bring research into production.
Key job responsibilities
Lead the design and development of foundational models and intelligent agent architectures tailored to enterprise use cases.
Partner with engineering, product, and UX teams to integrate generative AI into the Amazon Q assistant.
Drive experimentation to improve model accuracy, safety, latency, and cost efficiency.
Mentor other scientists and engineers, helping raise the technical bar across the team.
Contribute to and publish in top-tier conferences or file patents based on novel research contributions.
About the team
Amazon Q is a generative AI-powered assistant that helps employees become more productive by answering questions, generating content, summarizing data, and automating workflows using enterprise information. Our team builds the intelligence behind Q, leveraging large language models, retrieval-augmented generation, and agentic architectures to orchestrate complex workflows securely and at scale. We’re focused on building systems that reason, plan, and act across multiple modalities and business tools. As part of AWS’s broader Agentic AI initiative, we’re shaping the future of enterprise AI—empowering organizations to solve problems faster, reduce operational overhead, and unlock new levels of efficiency and decision-making.
