AI safety & policy
Full-time
Salary
£150,000 – £300,000
Routes to impact
Direct high impact on an important cause
Skill-building & building career capital
Description
Conduct interpretability research to understand and steer large AI models while developing practical tools for safe AI systems.
- Research model internals and interpretability mechanisms.
- Prototype techniques for analyzing and steering neural networks.
- Collaborate with engineers to deploy research into production tools.
- Publish findings and help shape future research directions.
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
