Tharun Chowdary Malepati

About

AI/LLM engineer who built and deployed a production healthcare RAG chatbot ("DoctorBot") with strict medical safety guardrails, an 85% confidence-gated verification layer, and latency optimizations that cut responses from ~8s to ~2–3s. Also worked on finflow.ai to generate finance/banking test cases from BRDs, collaborating closely with non-technical domain stakeholders, and has hands-on orchestration experience with LangChain/LangGraph and agentic evaluation/monitoring practices.

Experience

Education

Key Strengths

• Built and deployed a healthcare RAG chatbot (DoctorBot) to handle routine patient inquiries
• Strong focus on safety/reliability for medical AI (anti-hallucination guardrails; no diagnosis/prescribing)
• Implemented response verification with confidence gating (only show answers above 85% confidence)
• Performance optimization for RAG latency via semantic caching and pre-indexing (reduced ~8s to ~2–3s)
• Production-grade evaluation approach (golden dataset, automated tests, LLM-as-judge, A/B testing)
• End-to-end instrumentation and monitoring of LLM workflows (prompts, latency, token usage, step-level hooks)
• Experience orchestrating multi-step RAG pipelines with LangChain (intent classification, retrieval, reranking, citations)
• Able to translate technical concepts for non-technical stakeholders; ran regular feedback loops with domain experts