(Senior) Researcher, Misuse Risks

Lead SAIF's research on extreme misuse risks from frontier AI, building consensus between US and Chinese ecosystems on safeguards and international coordination.
- Run end-to-end dialogue programs convening AI researchers with biosecurity and counterterrorism experts across Western and Chinese institutions.
- Translate technical discussions into consensus artifacts, policy recommendations, and best-practice frameworks that both ecosystems can adopt.
- Track state of safeguards and developer practices in both ecosystems; scope and execute high-quality technical governance research projects.
- Requires substantive grounding in AI safety, security, or red-teaming; comfort navigating policy discussions and writing for decision-makers.
- Chinese-language capability and familiarity with biosecurity or cybersecurity strongly preferred; existing relationships in AI safety ecosystems desirable.

The Safe AI Forum aims to foster responsible governance to reduce catastrophic risks through shared understanding and collaboration among key global actors.