Sridhar Bokka

At Tata Consultancy Services, I lead quality validation for enterprise web applications, translating 100+ requirements into acceptance criteria and executing 80+ automated and grey-box test scenarios to deliver zero critical production defects at launch.

I've championed AI-driven test generation and automated evaluation in enterprise quality workflows, building executive QA dashboards that track release health, coverage, and defect metrics for data-informed release decisions.

In my AI-assisted LLM quality engine, I use Python, DeepEval, Groq API, Google API, Playwright, and TypeScript to evaluate accuracy, hallucination risk, toxicity, context relevance, and output consistency. I also turn unstructured specifications into test matrices and executable automation scripts, reducing test design time by 70%.

I've also built and validated a dynamic pricing model with Decision Trees and Random Forest, reaching 87% recommendation accuracy, and created Playwright CI/CD workflows that reduced multi-browser execution from 20 minutes to 5 minutes.