Fazl Barez
Principal Scientist @Martian
Signup · Get unlimited contacts
WORK HISTORY
Principal Scientist @Martian
Working on model routing, interpretability, and agent evaluation.
EDUCATION
University of Glasgow
Master of Science , Mathematical and Statistical Sciences
The University of Edinburgh
CDT Machine Learning/ Artificial Intelligence , Artificial Intelligence
University of Oxford
Doctor of Philosophy - PhD, DPhil Affiliate Student In Machine Learning
ABOUT FAZL BAREZ
Research Fellow at Oxford working on AI safety, interpretability, and governance. Collaborating with wonderful teams across Oxford, Cambridge CSER, and industry partners (Anthropic). Published high-impact research on crucial AI safety challenges- Mechanistic interpretability of LLMs- Deceptive AI and safety mechanisms- Safety evaluations and robust benchmarking- Machine unlearning and model editing- AI governance and policy frameworksBuilding novel solutions (stealth mode) to make AI systems more reliable and interpretable. Open to discussing research collaborations, industry partnerships, and investment opportunities in AI safety.I enjoy meeting new people - when connecting, please share a bit about what interests you!
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.