I design and ship production AI systems — LLM agents, RAG pipelines, and applied ML models — end-to-end from prompt/architecture design to deployment, with deep domain focus on healthcare AI.
Turning LLMs and ML models into reliable, production-grade AI systems
I'm an AI Engineer building agentic AI systems, RAG pipelines, and applied machine learning solutions — with a clinical/healthcare background that gives me an edge in designing AI for high-stakes, regulated domains.
My work spans the full AI engineering stack: LLM orchestration and agent design (Pydantic AI), retrieval-augmented generation with vector databases, prompt engineering, model deployment via FastAPI and Docker, and MLOps practices like model drift monitoring and responsible AI. I care about building AI systems that are not just accurate, but explainable, monitored, and production-ready.
AI Engineering first — backed by strong ML & data science foundations
Pydantic AI, tool-calling, multi-step agents
Pinecone, pgvector, embeddings, retrieval pipelines
Prompt engineering, Claude/GPT APIs, structured outputs
FastAPI, Docker, BentoML, model drift monitoring, CI/CD
Supervised & unsupervised models
CNNs, PyTorch, computer vision
Data analysis, ML, automation
Querying & data modeling
EDA, statistics, visualization
Linux, Git, Cloud Run, GCS
Explore my work and connect with me
Explore my open-source AI agents, RAG pipelines, and applied ML projects showcasing production-grade AI engineering and healthcare AI applications.
View RepositoriesConnect with me professionally to learn more about my experience, certifications, and contributions to the AI engineering community.
Connect NowLet's connect and discuss opportunities