NLResearch Fellows Program
TimaeusRemote
Global catastrophic risksAI safetyResearchSoftware engineering
Why this is on the board
Tenured mathematicians and physicists rarely work on the question of what happens inside an AI model during training, even though their fields, such as algebraic geometry or statistical physics, seem to have exactly the tools for it. As a fellow you keep your university position and lead your own line of research, with compute and a team. You publish methods that let others check whether a model has learned something other than what was intended.
This board is in beta and this is our judgement. If you think we have it wrong, tell us. Give feedback · How we reason about it
About the role
A research fellowship for tenured faculty and senior researchers applying learning theory to AI alignment while maintaining academic positions. - Lead independent research programmes on singular learning theory applications to interpretability, mechanistic analysis, and alignment. - Access computational infrastructure, internal tools, research community, and co-authorship opportunities with Timaeus. - Requires strong background in mathematics, theoretical physics, machine learning theory, stati…
Want to understand this first?
Start with our free course: about 100 minutes in six short units, at your own pace, with no sign-up. To go further, apply for the EA Fellowship: five weeks of reading and discussion in a small group. Also free, but selective.