NLResearch Resident, UK
Global catastrophic risksAI safetyResearchSoftware engineering
Why this is on the board
Here, research into what happens inside AI models and when they go off the rails goes straight to the people who train Claude, a system used by millions of people. Your project is scoped and your mentor sets the direction, so the biggest gain probably lies in the move itself: a young field with few experienced researchers gains a professor, founder or senior engineer, even one without a background in machine learning.
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 six-week to six-month paid research residency transitioning experienced technical leaders into full-time AI safety and alignment work. - Work on scoped empirical research projects in AI safety, alignment, interpretability, or security with direct mentorship from Anthropic researchers. - Access Claude models, GPU compute, and collaboration with the broader AI safety research community. - Ideal candidates: professors in quantitative disciplines, technical founders, or staff-level engineers mo…
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.