Harsh Mehta is an AI Engineer in Charlotte, NC with 5+ years across data science and machine learning, including 2+ years shipping production LLM systems. He currently builds RAG and LangGraph agent systems at Kaiser Permanente.

What does Harsh Mehta do at Kaiser Permanente?

He builds citation-backed RAG over 5,000+ pages of compliance documentation, with LangGraph agents and human-in-the-loop review. The work cut a 3-month policy review to one week and reclaimed roughly 300 analyst-hours per cycle.

Does Harsh Mehta have LangChain and LangGraph experience?

Yes. He has shipped LangGraph and LangChain multi-agent systems in production, including agent orchestration at Kaiser Permanente, the multi-agent core of the Ensemble booking platform on Vertex AI, and 7 multi-agent LLM workflows at ATC.

Is Harsh Mehta open to new roles?

Yes. He is open to AI Engineer, Machine Learning Engineer, and Data Scientist roles in Charlotte, NC and remote across the US.

Where did Harsh Mehta go to school?

He holds an M.S. in Information (Data, Machine Learning, Cloud) from the University of Wisconsin-Madison with a 3.95 GPA, and a Bachelor of Management Studies from the University of Mumbai with a 3.5 GPA.

What certifications does Harsh Mehta hold?

He holds the Databricks Data Engineer Associate, Snowflake SnowPro Core, Azure DP-100, Power BI PL-300, and AZ-900 certifications (all 2025), plus Salesforce Tableau.

← Back

Kaiser Permanente · May 2026 - Present · California - Remote

AI Engineer (Contract)

Policy assessment meant analysts manually cross-referencing 5,000+ pages of compliance documentation, roughly three months and 300 analyst-hours per cycle.

In healthcare an answer without a source is a liability, so the system was designed backwards: citations first. Every generated claim carries a page-level source attribution, anything the retriever cannot ground is refused rather than guessed, and humans stay in the loop for sign-off.

The eval set was not synthetic: every analyst rejection became a labeled case, so retrieval was tuned against "would an auditor sign this," not just precision@k.

Assessment cycle: 3 months to 1 week, ~300 analyst-hours reclaimed per cycle
Citation-backed RAG over 5,000+ pages of compliance docs with source-attribution guardrails
LangGraph agents with dynamic prompt routing and multi-tool orchestration
RAG knowledge assistant over distributed enterprise sources for self-serve domain Q&A
GitHub CI/CD for the agent system, build failures down 65%

RAGLangGraphCI/CDHealthcare