sathwik kuchana

About

Built and deployed an LLM-powered clinical decision support and risk monitoring platform for mental health at Valuai.io, emphasizing low-latency, evidence-grounded responses and crisis-safe behavior with clinician escalation. Strong production agent-orchestration background (LangChain/CrewAI) plus rigorous evaluation (clinician-in-the-loop + evaluator agent) and large-scale synthetic testing; also applied multi-agent workflows to document verification and fraud detection during an AI internship at Nixacom.

Experience

Education

Key Strengths

• Deployed safety-aware clinical LLM platform for mental health workflows in production
• Reduced LLM workflow latency 85% (8s to 1.2s) via re-architecture and Redis caching
• Built evidence-grounded RAG over PubMed + APA guidelines to reduce hallucinations and token usage
• Designed crisis detection + clinician escalation workflows for high-risk conversations
• Built scalable evaluation approach combining clinician scoring with automated evaluator agent
• Created large-scale test harness with 20,000+ synthetic patient profiles and regression checks
• Production-focused orchestration across routing, retrieval, guardrails, and downstream actions (LangChain/CrewAI)

Reference Highlights

• Led projects end-to-end from scratch (design through deployment)
• Strong leadership/ownership
• Built and deployed multi-agent architecture
• Focused on factual accuracy in healthcare AI (avoided factual inaccuracy)
• Effective communicator with non-technical stakeholders
• Able to work directly with clinicians and operations teams
• Explains model performance clearly to clinicians