At Phreesia, I designed AI-assisted agent workflows and built Selenium and Playwright automation for healthcare applications. I led QA across Scrum teams, including for a clinical software integration with EMRs, and worked on accessibility testing and release readiness.
In my independent AI quality engineering projects, I built evaluation harnesses for LLM and agentic systems, combining golden datasets, deterministic checks, and LLM-as-a-Judge scoring. My projects include a LangGraph change-risk agent, a healthcare RAG evaluation lab, and automated regression pipelines with quality gates.
