About Me
I'm a member of technical staff in the Microsoft Super Intelligence lab within Microsoft AI.
I work on evaluating LLMs. I have also worked on fairness in machine learning, semantic location understanding, and a few ranking and recommendation projects.
Before MSI, I worked on evaluating Llama at Meta, and before that I was at Google. I earned my PhD in Computer Science at the University of Washington.
For much more about what I've done professionally, check out my resume and Linked In profile.
Outside of work, I like birds, cumbia, punk rock and exercise.
Random Personal Projects
eBird Alert Email Map
A tool for showing the sightings from an eBird Needs alert email on a map. Paste an alert email and see all the reported sightings plotted on a Google Map, with species details and checklist links in each marker.
Try itClaude writes Thumby games
An early project in AI-assisted coding: two games for the Thumby keychain gaming device made with Claude.
The first is a version of Brian Eno and Peter Schmidt's Oblique Strategies cards (useful for shaking yourself out of a creative block). This went through a few revisions to get the final functionality. I edited about ~20% of the code myself.
The second is a Magic Eight Ball simulator. For that, I sent exactly six messages to Claude and edited 4 lines of code myself. Three of those messages were to iterate on functionality, and three were to point out hallucinations Claude made about the Thumby API.
Both are available in the Thumby Arcade.
eBird DB
A Python package for importing eBird CSV data into a Postgres database for easier, faster ad hoc querying.
It works directly with compressed data inside the zip or tar files that eBird provides (which can be upwards of 140GB), and has filters to limit what data is imported, so you can conserve local disk space.
Get it on GitHub