AI safety & policy
Full-time
Routes to impact
Direct high impact on an important cause
Description
Lead AI safety, security, and model evaluation research, setting the roadmap and shipping benchmarks, evaluations, and published work.
- Own the research roadmap across safety, security, red teaming, robustness, LLMs, agents, and multimodal systems
- Design benchmarks and evaluation methods that surface real vulnerabilities in frontier models
- Lead research collaborations with frontier labs, academic institutions, and technical partner teams
- Drive published research output, including one paper per quarter at top-tier conferences
- Work with engineering and product to turn research findings into deployed systems at scale
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.



