Naveen Kancharla

About

Built and deployed a production LLM-powered document Q&A system using a strict RAG pipeline (LangChain-style orchestration + FAISS) to help users query large internal document sets. Demonstrates strong reliability focus through hallucination mitigation, curated offline evaluation with grounding checks, and production monitoring (latency/fallback rates) plus stakeholder alignment via demos and business metrics.

Key Strengths

• Built and deployed a production LLM document QA system for internal knowledge search
• Practical hallucination reduction using strict RAG, similarity thresholds, and abstention behavior
• Structured evaluation approach combining offline test sets, manual retrieval validation, and grounding checks
• Production-minded monitoring and iteration using latency, fallback rates, and user feedback
• Able to debug complex multi-step LLM workflows via step-level logging and prompt versioning
• Thoughtful model/retrieval/prompt selection based on accuracy, latency, cost, sensitivity, and scale constraints
• Effective communication with non-technical stakeholders via demos and outcome-based success metrics

Reference Highlights

• Strong at designing and shipping LLM-based products
• Led an LLM-based QA document system end-to-end (architecture through deployment)
• Active and consistent communication (daily updates, progress communication)
• Resolves technical challenges effectively
• Plays a key role in shipping production solutions
• Works very well across teams and with non-technical stakeholders
• Aligns on requirements early
• Translates technical details into business-related terms
• Uses simple examples to explain technical concepts
• Ensures understanding through open discussion

Experience

Education

Skills

Languages

Certifications