I build safe, secure, and reliable AI and autonomous systems for critical environments. Most of my work sits at the intersection of research and engineering, with a focus on systems that have to work reliably in the real world.
- safe, secure AI and autonomous systems
- AI alignment, robustness, and runtime assurance
- onboard and edge intelligence for spacecraft and remote systems
- neuromorphic computing and adaptive learning
- robotics and physical-world autonomy
- model compression, quantization, and deployment
Engineering contributions merged into OpenAI, Google DeepMind, and The Alan Turing Institute codebases, spanning agent runtime safety, sandbox and tracing integrity, multi-agent systems, and scientific ML infrastructure.
149 merged upstream PRs across 24 upstream repositories
AI and ML
Acceleration and deployment
Robotics and perception
Hardware and edge
Space systems
Engineering and research
