AI safety & policy
Full-time
Salary
$174000 - $252000 (USD)
Routes to impact
Direct high impact on an important cause
Description
Drive empirical AI safety and alignment research on frontier models, focusing on understanding behavior, testing vulnerabilities, and developing practical safeguards.
- Define research data structures, frameworks, designs, and evaluation metrics
- Set up large-scale tests and deploy promising ideas quickly and broadly
- Identify gaps in existing technology and work with stakeholders to address them
- Publish research papers and contribute findings internally and to the wider community
- Develop long-term research directions through internal and external collaboration
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.



