AKHIL CHIPPALTHURTHY

About

GenAI/LLM engineer who architected and deployed a production RAG “research assistant” for JPMorgan Chase’s regulatory compliance team, focused on safety-critical behavior (mandatory citations, refusal when evidence is missing). Deep hands-on experience with LlamaIndex, Pinecone, Hugging Face embeddings, LangGraph agent workflows, and metric-driven evaluation (golden sets, TruLens), including a reported 28% relevancy lift via cross-encoder re-ranking.

Experience

Education

Key Strengths

• Built and deployed production RAG system for regulatory compliance research at JPMorgan Chase
• Designed safety-critical LLM workflow with mandatory citations and explicit “not in context” behavior to reduce hallucination risk
• Improved answer relevancy by 28% using cross-encoder re-ranking over initial vector retrieval
• Architected modular, swappable GenAI stack to adapt to evolving LLM components
• Strong agentic orchestration skills (stateful LangGraph workflows with self-correction and human approval gates)
• Rigorous evaluation approach: golden datasets, adversarial/jailbreak testing, and metric-driven iteration (TruLens/LLM-as-judge)
• Effective collaboration with non-technical legal/compliance stakeholders by reframing metrics around auditability and trust (attribution UI, live break-testing workshops)