I’m a research fellow at HAI and the Stanford Intelligent Systems Laboratory (SISL) funded by the Schmidt Sciences Foundation. Prior to this I built fun things at Amazon and Capella Space. I completed my PhD in Aerospace Engineering at Stanford under Mykel Kochenderfer. My work focuses on building robust decision-making into automated operational systems. I love solving hard problems with good people.
My current research is on automated red-teaming to aid in building robust AI systems for safety-critical applications with a focus on cybersecurity, mental health, and autonomous vehicle domains. I also have a strong interest in robotics and am working on developing world-model based-controllers to enable robots to learn how to accomplish complex tasks from a small number of experiences. My work generally combines a mix of techniques from optimization, decision-making, reinforcement learning, and control theory.
I was a founding engineer at Capella Space, the first US commercial synthetic aperture radar satellite imaging constellation. There I led the spacecraft operations group that successfully developed a fully-automated constellation operations system capable of delivering global high-resolution imagery on-demand without any human involvement. I subsequently led the constellation operations and space safety group at Project Leo (Kuiper). Most recently, I was a Principal Applied Scientist at Amazon Web Services, where I worked on building software services for large-scale distributed edge compute applications.
Weakly supervised automated language model red-teaming to identify low-perplexity toxic prompts. Develops methods for automated failure discovery in large language models for safety-critical applications.
Using world models to efficiently detect failures in autonomous systems, enabling robots and AI agents to learn robust behaviors from limited experience.
A modern, high-performance astrodynamics library for satellite orbit propagation, coordinate transformations, and time system conversions. Available in Rust and Python.
Optimal ground station selection for low-Earth orbiting satellites. Uses integer programming to minimize cost while maximizing data downlink coverage for satellite constellations.