I am a Postdoctoral Research Fellow at the University of British Columbia and BC Cancer, developing agentic AI systems for healthcare — including conversational assistants for cancer patients and clinicians. My work centres on design, evaluation, and reliability of large-scale agentic architectures and RAG systems in high-stakes clinical settings.

As Agentic AI Technical Specialist at the Vector Institute (2+ years), I have advised 10+ startups on production agentic AI — multi-hop RAG pipelines, tool-augmented agents, and rigorous evaluation frameworks for reliability and failure-mode analysis. At Amazon, I pioneered LLM-as-Judge and LLM-as-Jury pipelines for RAG evaluation, improving contact deflection by 2% and cutting manual review effort by four weeks.

I publish in ACM Computing Surveys (IF 23.8), IEEE, and ACM RecSys.