Contact
Get in Touch
Research discussions, collaboration, and opportunities in AI safety, reinforcement learning, and autonomous systems are welcome.
Contact
Primary email
Best long-term contact for research, collaboration, and professional opportunities.
Research Collaboration
I am particularly interested in discussions that connect safe continual reinforcement learning with broader problems in adaptive AI safety: predictive and proactive safety, runtime monitoring and intervention, long-horizon agent safety, and safety under novelty or unmodelled change.