Sep 2021 – Present · 4 yrs 8 mos · Hyderabad, Telangana, India · On-site

• Design and evaluate AI interactions by analyzing both single-turn and multi-turn conversations to ensure contextual accuracy, coherence, and response quality in large language models.
• Develop, validate, and optimize AI prompts using advanced evaluation frameworks like RAGAS and DeepEval to measure performance metrics such as context precision, recall, and answer relevancy in LLM systems.
• Leverage AI capabilities within Playwright automation to build intelligent, self-healing test scripts, reduce manual effort, and accelerate end-to-end testing with smarter test generation and maintenance.