Task Development Engineer
METR (Model Evaluation and Threat Research)RemoteGlobal catastrophic risksRecommended by an evaluator
This role is on our board because we think it is an unusually effective way to spend a career. How we reason about it
Free to leave the Netherlands? Look at 80,000 Hours, Probably Good and EA Opportunities first — the strongest opportunities are there. Why we say this
Why this is on the board
De metingen van METR — hoe lang een AI-model zelfstandig aan een taak kan werken — worden overgenomen in system cards van AI-labs en gebruikt door overheden voor beleid. Jij bouwt de taken waarop die cijfers rusten: één slecht gespecificeerde taak vertekent stil het beeld dat toezichthouders van AI-vooruitgang hebben.
About the role
We are a nonprofit research organization that develops scientific methods to assess AI capabilities, risks, and mitigations, with a specific focus on threats related to AI R&D automation and misalignment.
Requirements
| Language | English is enough |
|---|---|
| Work authorisation | Unclear |
| Screening | Not mentioned |
| Where you work | Remote (Europe) · Remote |
| Level | Mid level |
| Salary | Not stated |
| Posted | 1 August 2026 |
| Closes | No closing date given |
This takes you to the employer’s own site, where you apply.
More about METR (Model Evaluation and Threat Research)Why this problemGlossary
Curious?
If you want to know how we arrive at this list, we run a short intro course and a newsletter. Neither costs anything.