Job description
Beijing Academy of AI • Beijing, China
Beijing, China
- In this role, you'll establish risk identification and governance systems for large model security algorithms across various scenarios.
- Develop large-scale model security capabilities including human feedback technology and defense against command attacks.
- Implement risk assessment systems through red-blue confrontation and automated security capability evaluation.
- Research long-term risks emerging from rapid model capability improvements.
- Address new risks derived from applying large models to complex systems, tools, and decision-making capabilities.
Applications are handled by the employer.
AI Safety Careers does not process applications directly.
This listing may be aggregated from a public source or submitted by a third party. If you represent this employer and would like to update or remove this listing, contact .