Contributor

Core responsibilities:

• Be available to pick up research operations tasks for AI safety labs
• Provide evaluation implementation, data annotation, and administrative support
• Build and run evaluations, baselines, and benchmarks using frameworks like Inspect
• Manage quality data annotation pipelines and coordinate annotation teams
• Conduct red and blue team adversarial testing to identify vulnerabilities and improve system robustness
• Handle project administration, grant management, and operational overhead

This role contributes to AI safety by conducting evaluations and testing to identify vulnerabilities and improve system robustness, supporting research operations for AI safety labs.

Required skills and qualifications:

• Experience with evaluation implementation and data annotation
• Ability to build and run evaluations using frameworks like Inspect
• Experience managing data annotation pipelines and coordinating teams
• Knowledge of red and blue team adversarial testing methodologies
• Project administration and grant management experience

No benefits information provided in the job description.

No organization information provided in the job description.