For up-to-date info about what I've done and am up to see: www.radzaj.com

I'm a barrister (13 years in law, policy, & non-profit boards). I've spent 2026 exploring AI safety.

- I am currently a SPAR fellow bridging mech interp and law (mentor: Elija Perrier)(https://sparai.org/projects/f26/recLMwVX5XjlH9dx4/)
- I started 'Safe AI in Law', an org to build AI safety capability in the legal community (safeai.law).
- I completed model behavioural research (apartresearch.com/project/behavioural-indicators-of-fault-in-large-language-models-91jb)
- I co-authored an AI incident response paper (apartresearch.com/project/evidence-and-access-in-the-openaihugging-face-incident-wtyv)