At Writer AI, I designed and built the Writer Evals Platform from scratch, enabling dataset management, evaluators, runs, leaderboards, and human-review workflows for LLM, RAG, and agentic systems. I also built the evaluation SDK and lead model comparisons, judge calibration, and production-informed evaluation practice.
I've brought an automation-first quality mindset across Booking.com, ServiceNow, and Infosys, building API and UI test frameworks, CI pipelines, quality tooling, and release-risk processes. I enjoy turning complex product and reliability needs into practical platforms, repeatable evaluation systems, and faster feedback for engineering teams.

