Open to opportunities

Sanjay User

@sanjayuser6

Message

I build production RAG and generative AI platforms for healthcare, banking, and retail.

United States

Message

What I'm looking for

I'm looking to build reliable, scalable generative AI and RAG platforms where grounded retrieval, secure APIs, cloud deployment, and measurable model quality improve real-world workflows.

At Optum, I architect production RAG systems for enterprise healthcare knowledge platforms, combining ingestion, chunking, embeddings, hybrid BM25/vector search, and grounded response validation. I build secure FastAPI services with Azure OpenAI to support clinical summarization, Q&A, and workflow automation.

I’ve deployed HIPAA-compliant AI workloads on Azure Kubernetes Service, with RBAC, autoscaling, monitoring, token optimization, and evaluation frameworks for relevance, latency, and retrieval precision. My focus is making LLM systems reliable, scalable, and cost-conscious in production.

Previously at Capital One and Kroger, I built ML inference APIs, semantic search, NLP pipelines, Redis-backed performance improvements, and containerized deployments for financial and retail AI products.

Experience

Work history, roles, and key accomplishments

Current

AI/ML Engineer – Generative AI & RAG Systems

Current

Optum

Aug 2025 - Present (1 year 1 month)

Architected end-to-end RAG pipelines for enterprise healthcare knowledge platforms, improving contextual accuracy and reducing manual lookup effort. Designed multi-layer RAG architectures and implemented hybrid search combining semantic and BM25 retrieval.

RAG Lang Chain LlamaIndex Azure OpenAI fastAPI Python Docker Kubernetes Azure AI Search Pinecone Faiss Hybrid Search Prompt Engineering LLM Evaluation HIPAA RBAC Redis Async Processing

Senior Software Engineer – AI/ML Platforms

Capital One

Jun 2022 - Jul 2024 (2 years 1 month)

Designed scalable backend systems using Python and FastAPI for ML inference and NLP workloads. Implemented semantic search components and built RESTful APIs for model predictions, improving response times and search relevance.

Python fastAPI REST APIs Semantic Search Embeddings Redis Docker Kubernetes ML Inference NLP

Machine Learning Engineer – Retail AI Systems

Kroger

Apr 2021 - May 2022 (1 year 1 month)

Built end-to-end ML pipelines for data ingestion, preprocessing, feature engineering, model training, and cloud deployment on AWS. Implemented NLP-based product classification and embedding-based search ranking improvements.