AI safety & policy
Full-time
Deadline
2026-11-30
Routes to impact
Direct high impact on an important cause
Description
Build research infrastructure, evaluation pipelines and tools to test, evaluate and better understand frontier AI models and their risks.
- Develop and maintain evaluation pipelines and codebases for large AI models
- Turn research questions into practical experiments and prototypes alongside Research Scientists
- Contribute to new evaluations, interpretability methods, and safety benchmarks
- Support large-scale experiments, including distributed training and evaluation of models
- 24-month fixed-term contract
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.



