At Turing, I contribute to LLM evaluation and tool-use testing for coding, mathematical-reasoning, and data-analysis tasks. I design and test Python and JSON function-call scenarios, including multi-step sequences and dependencies.
I analyze complex prompts and model responses, label outputs against accuracy and quality criteria, and provide structured feedback on failure patterns.
Before Turing, I built application features and backend services at IDrive, Justdial, Mindlogicx, and BRISA Technologies Pvt. Ltd. My work included a custom Python web framework, gRPC microservice components, and Django-based applications; I also built Cricket Voice Lab, a browser application that generates cricket commentary audio.
