Adversarial attacks, security and interpretability of large language and vision models
Large Language Model Lead
Stability AI
Feb 2023 - Aug 2023(7 months)
Leading the Large Language Model research at Stability AI.
Research Scientist & Member of Technical Staff
Anthropic
Jan 2022 - Feb 2023(1 year 2 months)
Contributed to the development of Claude as an early Member of Technical Staff.
G
Google AI Resident
Nov 2018 - Sep 2019(11 months)
Understanding Deep Learning. I started research projects with Google Brain and DeepMind working on developing theoretical understanding of deep learning and using the insights to make it faster, easier, and more robust.
Education
verified_user
0% verified
Doctor of Philosophy (Ph.D, Artificial Intelligence
Stanford University
Jan 2016 - Dec 2022(7 years)
My research: https://scholar.google.com/citations?user=eu2Kzn0AAAAJ
Master of Science (MS, Theoretical and Mathematical Physics
Stanford University
Jan 2016 - Dec 2018(3 years)
Master’s Degree (MSc), Trinity College, Theoretical and Mathematical Physics