NLResearch Engineer, Novel AI Platforms for Multiscale Alignment
Future of Life FoundationRemote
Global catastrophic risksAI safetySoftware engineeringResearch
Why this is on the board
Many ideas for getting AI systems to work together safely still exist mostly on paper, because there is no good environment to test them in. You build those test environments, and other AI safety researchers then use them to test their theories against working systems.
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
Develop novel AI platforms and agent systems addressing alignment challenges while combining infrastructure engineering with safety research. - Design and implement architectures for multi-agent execution environments, conflict resolution mechanisms, and cooperative AI systems with alignment properties. - Develop optimisation algorithms, testing frameworks, and middleware components to validate theoretical alignment approaches and facilitate secure agent communication. - Build reusable softwa…
More about Future of Life FoundationWhy this problemGlossary
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.