Different industries, same starting point: sitting with the team, learning how the work actually gets done, before any code gets written.
Investment Research Platform
I've been building an investment firm's research infrastructure from scratch. Started by learning how their analysts work day to day. Built screening and scoring tools, report generation from quick screens to deep dives, and a dashboard that pulls together earnings transcripts, research notes, and portfolio data from half a dozen sources. The work keeps expanding because the tools get used.
Production ML Pipeline Assessment
A lending company with credit models in production wanted an outside review of their ML pipeline. Training features are built in their data warehouse; to serve live decisions, engineering re-implements each one by hand in a separate service, and that recoding loop slowed every model launch. I interviewed the data science and engineering teams on both sides of that handoff, traced one feature through the full pipeline code, and mapped how the system works today. The deliverable was a written assessment: a sequenced set of recommendations with the reasoning behind each, for their team to build.
Clinical Document Generation
Started as a technical assessment, turned into ongoing work. The problem: turning messy healthcare PDFs into regulatory documents where the structured data has to be near-perfect. Tables, citations, cross-references — the parts where LLMs aren't reliable on their own. The AI handles the extraction and reasoning, but the final output is generated deterministically so it's reproducible and auditable. I also built the testing infrastructure so every section gets measured against expert ground truth.
Context Engineering for Platform Migration
An engineering team rebuilding core infrastructure needed to get organized about how they use AI during a major migration. I built the system around it: shared docs that stay current with the architecture, automated digests that pull key decisions out of team conversations, and a linked wiki that gives every AI session real context about the codebase. Now I work with the engineers one-on-one as they use agents to do the migration itself: moving a large production codebase to a new language, piece by piece.
Predictive Scheduling Model
Built and shipped a production ML model that predicts optimal scheduling windows. Trained an ensemble on historical data, validated with back-testing, and deployed an inference endpoint running real-time predictions inside their app.
Applied AI Faculty Workshop
Designed and ran an all-day AI workshop for faculty at a large university hospital. Worked with their leadership to understand what they were struggling with, then built a curriculum around that. Hands-on exercises, follow-up videos.
Have a problem that fits?
Tell me what you're working on and I'll be straight about whether I can help.
Start a conversation