Software engineering, applied AI, and machine learning
I build software and write about what I learn.
I've spent more than 20 years building software and roughly a decade working in ML and AI. Today my work focuses on applied AI, production ML, and software engineering. I write here about the work and what I learn from it.
Recent writing
All posts →Five Lessons from Putting AI Into Research Teams
Which tasks to automate, where analysts push back, and how to tell if a workflow is quietly getting worse - five lessons from a...
How I Use Modal
A tour of two practical Modal deployment patterns: cron jobs, secrets, volumes, static IPs, web apps, background AI jobs, and sandboxes, all in plain...
Building the Multiplayer Institutional Brain
I joined Khe and Brett on the Invest with AI podcast to talk about how investment firms move from individual AI experimentation to a...
There's More Public Data Than People Exploring It
I used Claude Code to connect open federal energy datasets into WattsOpen, an interactive site about where the grid has room. It started as...
Automating the Path from Frontier Models to Fine-Tuned Models
A tweet about fine-tuning on frontier model outputs got me thinking about how much of that loop could be automated.
Projects and conversations
AI in Research Teams
Lessons on choosing research tasks, keeping judgment with analysts, and checking whether the output stays reliable.
Open the guide →Deploying AI on the Buyside
A conversation with Brett Caughran and Khe Hy about moving from individual experiments to shared workflows.
Listen to the episode →WattsOpen
An interactive site that connects federal energy datasets to map power plant retirements, grid infrastructure, and interconnection queues.
Explore WattsOpen →I do client work through PragmaNexus. Its site has services, case studies, and contact information.
Visit PragmaNexus →