NLAIXI Labs Research Fellowship
AIXI LabsRemote
Global catastrophic risksAI safetyResearchSoftware engineering
Why this is on the board
A lot of AI safety research is mathematically rigorous but too narrow, or practically usable but too opaque to base hard safety claims on. As a fellow you spend about three months on methods that are both general and verifiable, and you publish them. So the leverage lies not in your own hours but in whether other researchers adopt your results, and with work like this that is never certain.
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
Quarterly research fellowship pursuing AI safety through algorithmic information theory and modern LLM agents. - Conduct self-directed research project spanning foundational theory to empirical LLM and reinforcement learning work. - Publish papers and written outputs communicating results to AI safety and ML research communities. - Requires PhD-level research background or master's mathematics with substantial industry experience. - Requires solid grounding in probability, statistics, informa…
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.