Summary

Researcher role focused on developing and evaluating frontier AI safety mitigations across interpretability, alignment, control, and robustness. The working arrangement and location are not specified.

Responsibilities

• Identify emerging artificial intelligence safety risks
• Build and refine frontier risk evaluations
• Set research directions for safer aligned systems
• Develop novel safety mitigation techniques
• Design red-teaming pipelines for robustness testing
• Create guidelines for artificial intelligence safety