At Bebo Technologies, I test enterprise web platforms and AI-powered products across manual, automation, API, functional, integration, and regression cycles. I've designed and executed 100+ test cases per sprint and built Selenium and Playwright frameworks that reduced regression testing time by 40%.
I validate Agentic AI, LLM, and RAG applications for accurate, reliable behavior, including MCP integrations, LangGraph orchestration, LangSmith and LangFuse observability, prompt regression, hallucination detection, guardrails, and OpenAI API tool calling.
I've owned QA for Salesforce CRM workflows, a Salesforce Lightning migration delivered with zero critical post-launch defects, and a vehicle booking platform with an AI chatbot and recommendation engine. I use Python, Pandas, NumPy, and model-evaluation metrics to identify output-quality issues before release.
