Narayanaroyal Marisetty

About

Designed and deployed an enterprise LLM-powered clinical/pharmacy policy knowledge assistant at CVS Health, replacing manual searches across PDFs/Word/SharePoint with a HIPAA-compliant RAG system. Built end-to-end ingestion and orchestration (Airflow + Azure ML/Data Lake + vector index) with PHI masking, versioned re-embedding, and production monitoring (Prometheus/Grafana), and partnered closely with clinicians/compliance to ensure policy-grounded, auditable answers.

Experience

Education

Key Strengths

• Built and deployed an enterprise LLM/RAG knowledge assistant for clinicians in a HIPAA-regulated environment
• Strong unstructured data integration: custom extraction + normalization into a canonical format across PDFs/Word/SharePoint
• Reliability-focused evaluation: unit tests for pipeline components plus retrieval benchmarks and SME ground-truth validation
• Production-grade MLOps: Dockerized pipelines, CI/CD with Terraform/GitHub Actions, monitoring with Prometheus/Grafana
• Improved retrieval precision via chunking improvements, medical abbreviation expansion, and embedding drift monitoring
• Efficient corpus maintenance through document versioning and selective re-chunking/re-embedding
• Cross-functional collaboration with clinicians and compliance to translate policy needs into RAG metadata, prompts, and safety controls