I build AI systems that reason, retrieve, and act.
AI/ML Engineer with 5+ years shipping production AI across financial services and healthcare — multi-agent orchestration, RAG, LLM systems, and end-to-end MLOps.
Press ⌘ K to navigate this portfolio like a command center.
I'm an AI/ML engineer focused on Agentic AI and the systems that make large models useful in the real world. Over the last five years I've designed and scaled production AI across financial services and healthcare, from multi-agent orchestration to enterprise RAG pipelines.
My work sits where research meets operations: LangChain, LangGraph, and the Model Context Protocol for orchestration; vector databases and knowledge graphs for retrieval; and FastAPI, Kubernetes, and MLflow for the MLOps that keeps it all running and auditable.
I care about the parts people skip — governance, interpretability, and compliance — so the systems I ship hold up under GDPR, HIPAA, and FINRA scrutiny, not just in a demo.
Run a browser-only RAG simulation, inspect the pipeline stages, and explore case studies grounded in my production experience. This is an interactive portfolio demo—not a hosted language model.
Specialized agents orchestrated over enterprise APIs, policy documents, vector stores, and compliance checks.
Hybrid retrieval, reranking, vector memory, and evaluation loops designed to reduce hallucinations.
Readmission, length-of-stay, clinical NLP, and multimodal CV pipelines deployed with compliance controls.
Telemetry, drift monitoring, automated retraining, and production controls for model and LLM services.
Amazon Web Services
Microsoft
Open to AI/ML and Agentic AI engineering roles. The fastest way to reach me is email — I usually reply within a day.
A styled preview of my profile — the button opens my real LinkedIn in a new tab.
View full profile →