Vishruth V
Senior Ai Ml Engineer Generative Ai & Rag Systems @HCA Healthcare
Signup · Get unlimited contacts
WORK HISTORY
Senior Ai Ml Engineer Generative Ai & Rag Systems @HCA Healthcare
Architected end-to-end RAG pipelines for enterprise healthcare knowledge platforms, enabling clinical teams to retrieve accurate, grounded answers from unstructured documents at scale.• Designed multi-layer RAG architectures covering ingestion, chunking strategies, metadata enrichment, embedding generation, and vector indexing — eliminating manual lookup across siloed clinical systems.• Implemented hybrid search combining semantic vector similarity (Pinecone / FAISS) and BM25 keyword retrieval, significantly improving retrieval precision across diverse clinical query types.• Built secure LLM-powered APIs using Python and FastAPI with async processing, delivering low-latency, production-ready endpoints supporting enterprise healthcare workflows.• Integrated Azure OpenAI models for clinical document summarization, Q&A, and workflow automation — reducing clinician review time and accelerating decision-making.• Developed hallucination mitigation strategies using grounded retrieval and response validation pipelines, ensuring factually trustworthy AI outputs compliant with healthcare standards.• Containerized AI workloads with Docker and deployed on Azure Kubernetes Service (AKS) with autoscaling, ensuring fault-tolerant availability under variable clinical traffic.• Implemented RBAC-enforced AI access controls meeting HIPAA security requirements and built monitoring for token usage, latency, error rates, and embedding pipeline performance.
EDUCATION
University of North Texas
Master's degree, Artificial Intelligence
ABOUT VISHRUTH V
I build production-grade AI systems that make healthcare smarter and safer.At HCA Healthcare, I architect end-to-end RAG pipelines that give clinical teams real-time access to knowledge buried across enterprise documents combining semantic vector search with BM25 hybrid retrieval to surface accurate, grounded answers at scale. I\'ve built LLM-powered FastAPI services with sub-second latency, designed HIPAA-compliant RBAC systems, and deployed containerized AI workloads on Azure Kubernetes Service that scale automatically with clinical demand.Before specializing in AI, I spent years at Capital One and Kroger building ML inference infrastructure, NLP pipelines, and embedding-based search systems which means I understand both the research side and the operational reality of running AI in production.What I care most about: retrieval quality, factual grounding, and making sure AI systems are trustworthy — not just impressive.Core expertise:→ RAG pipeline design (ingestion · chunking · vector indexing · hybrid search · response validation)→ LLM integration: Azure OpenAI, OpenAI API, LangChain, LlamaIndex→ Vector databases: Pinecone, FAISS, Azure AI Search→ FastAPI · Python · Docker · Kubernetes · GitHub Actions→ HIPAA-compliant AI · Token optimization · LLM evaluation frameworksM.S. Computer Science (AI Specialization) · University of North TexasAWS Certified AI Practitioner
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.