Skip to content

Work With Me

I’d love to connect if your team is:

  • Building an LLM workflow that needs to turn unstructured documents or conversations into reliable structured outputs
  • Working on extraction, classification, routing, or review workflows and struggling to make the system dependable in practice
  • Looking to improve evaluation so your AI workflow is trustworthy enough for real operational use
  • Trying to move from a promising prototype to a system that fits into an actual business process

If your team is building an LLM workflow for extraction, classification, or routing and you need it to be more reliable in practice, feel free to book a time here.

My Background

Previously, I’ve worked on a variety of machine learning and LLM projects including a computer vision system for a Fortune 500 client and an LLM-powered chatbot for a leading publisher built on top of a large content archive.

While my background is broader than LLM workflows alone, the area I’ve chosen to focus on is turning unstructured documents and conversations into structured outputs that can be used reliably inside real business workflows.

What I’ve learned is that the hard part is usually not getting a model to produce an answer. The hard part is making the overall system dependable enough to use in practice. That is where evaluation, review, and workflow design become critical.