About Me

I'm a Staff Data Scientist who builds AI systems that actually talk to customers — not just models that live in notebooks.

Right now, I work at a customer experience analytics company where I designed and own a production conversational AI system from the ground up. Think multi-agent architecture, LangGraph orchestration, Azure OpenAI, and Snowflake powering real customer-facing interactions every day. It's the kind of work where "it works on my machine" isn't good enough — it has to work at scale, reliably, for real people asking real questions.

How I Got Here

My path into AI wasn't a straight line. I started deep in the data world — writing complex SQL, building analytics platforms, and making sense of messy survey data at scale. Over time, I kept gravitating toward the question: what if the data could talk back?

That pull led me from traditional data science into the world of AI agents, retrieval systems, and production ML. I went from someone who analyzed customer feedback to someone who builds systems that can reason about it autonomously. The recent promotion to Staff was a milestone, but the work that got me there — architecting multi-agent systems, solving gnarly context window problems, wiring up retrieval pipelines — that's the stuff I actually get excited about.

What I'm Into

At work, I live at the intersection of AI engineering and data infrastructure. Multi-agent coordination, LangGraph, retrieval-augmented generation, prompt engineering that actually holds up in production — these are my daily tools. I care a lot about building AI systems that are robust, not just clever.

After hours, I'm usually tinkering on side projects. Currently I'm building a blackjack card counting trainer (codename: Rain Man()) because apparently I find probability math relaxing. I've also been experimenting with a voice-controlled teleprompter app for macOS. If it involves Python, a weird API, and a problem nobody asked me to solve, I'm probably already halfway through a prototype.

On the learning side, I try to read at least one AI research paper or deep technical post per week. I keep a running tracker of everything I've read — partly to stay sharp, partly because the field moves so fast that last month's breakthrough is already old news.

Experience

Staff Data Scientist — [Company Name]

[Start Date] – Present

  • Designed and built a production conversational AI system from the ground up using multi-agent architecture, LangGraph orchestration, Azure OpenAI, and Snowflake
  • [Add bullet point]
  • [Add bullet point]

[Previous Role] — [Company Name]

[Start Date] – [End Date]

  • [Add bullet point]
  • [Add bullet point]
  • [Add bullet point]

[Previous Role] — [Company Name]

[Start Date] – [End Date]

  • [Add bullet point]
  • [Add bullet point]

What This Site Is

This is where I write about the stuff I'm learning and building — production AI architecture, lessons from shipping multi-agent systems, interesting papers I've read, and the occasional side project deep dive. If you're into applied AI, building things that work beyond a demo, or just want to nerd out about agent orchestration, you're in the right place.