Manish Yamsani

About

Built a production multi-agent orchestration platform to automate healthcare claims and HR workflows, combining LangChain/CrewAI/AutoGPT with RAG (FAISS/Pinecone) and fine-tuned open-source LLMs (LLaMA/Mistral/Falcon) in private Azure ML environments to meet HIPAA requirements. Emphasizes rigorous agent evaluation/observability (trajectory eval, adversarial testing, LLM-as-judge, drift monitoring) and reports measurable outcomes including 35% faster claims processing and 40% fewer chatbot errors.

Experience

Education

Key Strengths

• Built and deployed production-grade multi-agent system for healthcare claims and HR workflows
• HIPAA-focused architecture using private, enterprise-governed Azure ML environments with open-source LLMs
• Designed RAG pipelines (FAISS/Pinecone) for secure document retrieval
• Reduced hallucinations via chain-of-thought prompting and fine-tuning (LLaMA/Mistral/Falcon)
• Agent evaluation rigor: trajectory analysis, adversarial tests, component benchmarking, LLM-as-judge
• Production monitoring with distributed tracing and model-drift alerts
• Demonstrated business impact: 35% reduction in claims processing time and 40% reduction in chatbot errors
• Strong cross-functional communication translating AI concepts into business outcomes for non-technical stakeholders