Staff AI/LLM Engineer
Staff AI/LLM Engineer with 12+ years building high-scale distributed systems and production Generative AI (GenAI) platforms. Built and led teams of 5+ engineers to ship Retrieval-Augmented Generation (RAG) pipelines, multi-agent workflows, and full-stack SaaS products achieving 95% accuracy, 20% cost reduction, and 99.99% availability. Driven by a belief that stable, well-architected systems free teams to move fast and think big, not worry about what might break. Actively seeking Staff AI/LLM Engineer roles (Remote-first).
Why this work matters
I build GenAI products, RAG pipelines, and agentic workflows. The focus is always on reliability, real impact, and code that holds up under production load.
Why I do this
Good engineering should give teams the stability to stop worrying and just build.
Most AI projects fail not because the model was wrong, but because the system around it wasn't built to last. I care about the parts that aren't glamorous: reliability, observability, and making sure things still work six months after launch.
How I help
Featured work
Frontline managers lose hours every week to overstaffing, no-shows, and last-minute schedule changes. I built a LangGraph multi-agent system with autonomous scheduling and staffing logic that gives workforce managers real-time decisions without the guesswork.
LangGraph
Manual market research is slow, inconsistent, and hard to scale. I built an agentic pipeline using LangGraph and OpenAI tool-calling that autonomously browses the web, synthesizes findings, and delivers structured reports on demand.
LangGraph · OpenAI
Repetitive refund requests drain support teams and frustrate customers. I built a conversational AI agent with policy reasoning and escalation logic that handles refund inquiries end-to-end without human intervention.
Conversational AI
Recruiters lose hours screening candidates without getting real signal. I built a GenAI persona grounded in my professional background that lets anyone get instant, accurate answers about my experience anytime.
GenAI
Planning multi-stop routes manually wastes time for drivers and field teams. I built a full-stack optimization app using Next.js and FastAPI that generates efficient stop sequences in seconds.
Next.js · FastAPI
Ready to connect?
Here's the simplest way to go from here.
Scroll through the work and get a sense of how I think and what I've shipped.
If you're hiring for a Staff AI/LLM role or building something in the AI space, there's probably something worth talking about.
Send a message. No formalities needed.
