Sruthi Kondapalli

About

Built and deployed a scalable, production-ready LLM knowledge assistant using a RAG architecture (LangChain + vector store/FAISS) to replace keyword search for internal documents. Demonstrates hands-on expertise in hallucination reduction and retrieval quality improvements through semantic chunking, similarity tuning, prompt design, and human-in-the-loop validation, plus strong stakeholder communication via demos and visual explanations.

Experience

Education

Key Strengths

• Built and deployed a production RAG-based LLM knowledge assistant for internal document Q&A
• Deep practical focus on reducing hallucinations via prompting, retrieval tuning, and confidence rules
• Strong retrieval quality optimization (semantic chunking, chunk overlap/size experiments, similarity tuning)
• Modular AI workflow design with clear success criteria and measurable evaluation (latency/accuracy/relevance)
• Structured testing approach (unit + end-to-end + benchmark queries) for LLM workflows
• Effective collaboration with non-technical stakeholders using demos, diagrams, dashboards, and iterative feedback