Research Contractor
FutureSearchRemote
Global catastrophic risksAI safetyResearchSoftware engineering
Why this is on the board
You design research tasks that FutureSearch uses to measure whether the latest AI models check their sources and are honest about what they don't know. Tests like these help shape how others assess those models, so one well-built task gets used far more often than you will ever run it yourself.
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
Research contractor developing training and benchmarking tasks for frontier AI models through careful information retrieval and analysis. - Conduct detailed research tasks including academic paper analysis, financial document cross-referencing, and source verification. - Leverage web research LLM tools effectively while maintaining calibration on uncertainty and tool limitations. - Communicate reasoning and findings clearly in both synchronous and asynchronous formats. - Requires strong resea…
Not the right role? Get new ones every month
On the first Tuesday of every month: new jobs and programmes from this board, plus events in the next six weeks and the best of the EA Forum.
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.