Varun Gattamaneni

About

Healthcare-focused LLM engineer who deployed a production triage and clinical knowledge retrieval assistant using RAG and LangGraph-orchestrated multi-agent workflows. Emphasizes clinical safety and compliance with robust hallucination controls, HIPAA/PHI protections (tokenization, encryption, audit logging, zero-retention), and human-in-the-loop escalation; reports a 75% latency reduction in a healthcare agent system.

Experience

Education

Key Strengths

• Built and deployed healthcare LLM triage + clinical knowledge retrieval system using RAG and multi-agent workflows
• Strong hallucination-mitigation design (RAG grounding, confidence thresholds, output classifiers, human fallback)
• HIPAA/PHI-safe architecture (tokenization, encryption, scoped access, zero-retention, audit logging)
• Designed reliable human-in-the-loop escalation with ticketing API handoff and full-context transfer
• Orchestrated stateful multi-agent workflows with LangGraph; reported 75% latency reduction and improved response consistency
• Rigorous agent evaluation approach (synthetic/adversarial tests, SME golden sets, shadow evals on live traffic)
• Pragmatic model/retrieval selection balancing accuracy, latency, cost, safety; chose fine-tuned model for clinical QA reliability