Principal Software Engineer, Agentic AI DevOps

Come help us build the AWS DevOps Agent to help customers quickly resolve and prevent operational issues in their production systems!

We are seeking a Principal Engineer to join the AWS DevOps Agent team, where you'll play a pivotal role in building agentic AI solutions to accelerate incident response and drive continuous operational improvements for production systems for Amazon-internal and external customers. This role focuses on building our agents that resolve incidents and use past incidents and best operational practices to improve our customers' systems. You will also help lead the strategy for our application map (topology) service.

Your work will directly contribute to advancements in AI-driven developer tools. You will work on a frontier agent, utilizing information retrieval systems, knowledge graphs, and large language models (LLMs).

We operate at the intersection of AI and DevOps, working on solutions that use generative AI technologies to improve the developer experience for builders who develop and operate applications on AWS. We help builders resolve incidents quickly in live systems, and then learn from those incidents to make systemic improvements.