At a software services company serving healthcare and financial-services clients, I test GenAI applications end to end, checking RAG outputs, prompt and response accuracy, safety guardrails, and AI feature regressions. I also configure Cline via MCP to generate test cases and automate workflows with Reflect.run.
I designed AIEvalcore, a Playwright-based framework for evaluating RAG and LLM quality, with Excel and HTML reporting and a command-line tool; I implemented it with AI assistance. Earlier, at a global IT services company, I led QA delivery and directed an offshore team across ETL, business intelligence, and enterprise application testing.
