About
I'm a computer scientist with a passion for research and developing AI systems that are transparent, reliable, and useful.
I graduated with High Honors from Oberlin College in Computer Science with a minor in Mathematics. My honors thesis explored multi-agent reinforcement learning and game theory, and I've continued developing that work independently since graduation.
I joined Google to learn how to turn research ideas into working systems. Over five years, I led applied research on LLM-driven developer automation and developed methods for constructing structured training data from large C++/Java codebases. I collaborated with DeepMind and CoreML on data specifications for Google's internal models and developed an unsupervised approach to root-cause diagnosis for Android using clustering on T5X embeddings.
My research focuses on interpretable AI and data-efficient reinforcement learning, and I'm currently applying to PhD programs in computer science.
Outside of work, I create digital images using linear optimization and constraints, building on independent research with Professor Robert Bosch at Oberlin. You can find my art and methodology at madebymath.art.