✨ About The Role
- The role involves identifying emerging AI safety risks and developing new methodologies to explore their impacts.
- The candidate will build and continuously refine evaluations of frontier AI models to assess identified risks.
- They will design and implement scalable systems and processes to support these evaluations.
- The position includes contributing to the refinement of risk management practices and best practice guidelines for AI safety evaluations.
- The job requires close collaboration with various teams to ensure comprehensive AGI preparedness.
âš¡ Requirements
- The ideal candidate is passionate and knowledgeable about both short-term and long-term AI safety risks.
- They should possess a robust "red-teaming mindset" and be able to think creatively to address challenges.
- Experience in machine learning research engineering and observability is essential for this role.
- The candidate should be capable of operating effectively in a dynamic and fast-paced research environment.
- Strong project management skills are necessary to scope and deliver projects from start to finish.