Hi!

I’m a PhD candidate at Imperial College London with an interest in how to make reinforcement learning safe for use in critical situations. I’m a part of the Verification of Autonomous Systems (VAS) group. I’m also associated with the CDT for Safe and Trusted AI.

I was previously working on AI safety as a visitor at FHI, University of Oxford. My master’s thesis from EPFL was also on this subject, although, my master’s programme at EPFL was in computational neuroscience. My bachelor’s degree was from KTH in biochemical engineering. For more information, see my LinkedIn.