About

I'm a computer scientist with a passion for researching and developing AI systems that are interpretable, reliable, and useful. Most recently, I spent five years as a software engineer at Google, turning ideas into working systems. I started in 2019 as an Engineering Resident.

At Google, I led research in LLM reasoning for out-of-distribution tasks by delevoping a chain-of-reasoning framework that enabled automated test generation for AndroidOS. I also collaborated with DeepMind and CoreML to train internal LLMs on AndroidOS, developed an unsupervised approach to root-cause analysis for Android Infrastructure errors, and led the Android Mainline API-correctness and coverage infrastructure.

Before Google, I graduated with High Honors in Computer Science from Oberlin College, with a minor in Mathematics. My honors thesis explored multi-agent reinforcement learning and game theory.

I'm currently applying to PhD programs focused on interpretable AI, with research interests in program synthesis & library learning, concept learning and causal interpretability, and sample-efficient reinforcement learning.

As a side-passion, I make digital art using linear optimization algorithms, building on independent research with Professor Robert Bosch at Oberlin. You can find the images and the methodology behind them at www.madebymath.art.

Research Highlights View all →