About
Peter Choi is a Principal Research Software Development Engineer at Microsoft Research, where he works in Catalyst Lab, the lab’s agentic AI experimental engineering team. His responsibilities include building the engineering and tooling backbone for agentic AI research, designing multi-agent systems and agent-skill frameworks, and helping turn early research prototypes into product-ready systems. Before joining Microsoft, Peter spent nine years at Amazon Web Services (AWS) building and shipping distributed cloud services at hyperscale, including multi-agent orchestration systems, with a focus on AI agent systems and application security.
Peter holds a Bachelor of Information Technology from Queensland University of Technology (QUT) and previously studied Information Technology and Electronic Engineering at Handong Global University. Earlier in his career he held software engineering roles across enterprise, cloud/IoT, and insurance domains in Australia, and completed his first research work on participatory sensor networks at QUT’s MQUTeR e-Research Centre. His areas of focus include agentic AI, large language models, retrieval-augmented generation, and inference efficiency.