About
I’m a Principal Applied Science Manager on Microsoft’s CoreAI team, where I lead an applied research group dedicated to boosting developer productivity with ML and AI. We’re currently advancing GitHub Copilot’s capabilities — Completion, Chat, Code Review and Agentic — to deliver smarter, more context-aware assistance through continual model refinement and in-context learning.
Key research and engineering challenges include:
-
Elevating LLM quality for developer-centric tasks via iterative training, feedback loops and real-world usage signals.
-
Harnessing code structure and context— leveraging syntax, semantics and repository context enrich both training and inference.
-
Scaling responsive code generation to enable fast, interactive experiences for millions of developers.
I thrive at the intersection of cutting-edge research and large-scale deployment, turning AI breakthroughs into tools that make every developer more effective.