Vasavi Mittapalli

About

Built and deployed a production LLM-powered RAG assistant for semiconductor manufacturing failure analysis, reducing engineer triage effort by grounding outputs in retrieved evidence and gating responses with SPC + ML signals (LSTM anomaly scores, XGBoost probabilities). Experienced with LangChain/LangGraph to ship reliable, observable multi-step agents with branching/fallback logic, and evaluates impact using both technical metrics and business KPIs like mean time to triage and downtime reduction.

Experience

Education

Key Strengths

• Built and deployed production-grade LLM RAG system for semiconductor failure analysis
• Strong hallucination mitigation via structured prompts, citations, no-answer paths, and schema-constrained outputs
• Uses non-LLM statistical/ML signals (SPC, LSTM anomaly scores, XGBoost probabilities) to gate LLM outputs
• Designs agents as composable, testable pipelines with clear success metrics
• End-to-end evaluation approach: offline test sets, edge cases, A/B testing, and production monitoring
• Ties agent performance to business outcomes (reduced mean time to triage, fewer reopens, improved engineer acceptance, downtime/cost reduction)
• Production agent reliability engineering using LangGraph branching, retries, and fallback paths
• Effective collaboration with non-technical stakeholders by translating workflow needs into agent behaviors and measurable metrics