Yashwanth Penugonda

About

Built and deployed a production LLM-powered RAG knowledge system to unify operational/policy information across PDFs, wikis, and databases, emphasizing auditability and low-latency/cost performance. Improved answer relevance at scale by moving from pure vector search to hybrid retrieval with metadata filtering and reranking, and partnered closely with healthcare operations/compliance to define acceptance criteria and human-in-the-loop guardrails.

Key Strengths

• End-to-end ownership of production LLM/RAG system design and deployment
• Designs for accuracy and auditability via retrieval gating and validation (not prompt-only)
• Scales retrieval quality as corpus grows (hybrid retrieval + metadata filters + reranking)
• Performance and cost optimization using p95 latency targets, token caps, top-k tuning, and model routing
• Builds reliable agent/workflow systems with explicit state machines, bounded steps, timeouts, retries, and fallbacks
• Metrics-driven evaluation and iteration (grounding rate, precision@k, latency, token usage) with instrumentation and controlled rollouts
• Strong cross-functional collaboration with healthcare operations/compliance; defines acceptance criteria and human-defer conditions

Experience

Education

Skills

Languages

Certifications