I’m a independent AI safety and governance researcher and MATS 10.0 fellow. I have an MSc in theoretical physics from the Australian National University, and experience across technology and government sectors, specialising in nuclear non-proliferation and safeguards, research software engineering for science, and foreign affairs.
My current research focuses on the development of concepts and techniques for verification of AI hardware and workloads. I previously co-led a project simulating compute permit markets for frontier AI. I also have an interest in principled AI safety research, helping build AI safety as a science, as well as using AI for science more broadly.
Please reach out if you have a shared interest in these fields!