Technical AI Governance Researcher

• Conduct empirical AI governance research and translate findings for policymakers.
• Design and run experiments examining frontier model behaviour on governance-relevant questions.
• Build and analyse datasets from model documentation, reports, and policy texts quantitatively.
• Create data visualisations and technical commentaries addressing AI governance and safety developments.

This role directly contributes to shaping AI governance policies that ensure safe and beneficial development of frontier AI systems, reducing risks from advanced AI.

• Experience in AI governance research or related empirical research.
• Ability to design and run experiments on frontier model behaviour.
• Skills in quantitative data analysis and dataset construction.
• Proficiency in data visualisation and technical writing.

Compensation and benefits not specified in the posting.

Centre for AI Security and Access is an organization focused on AI safety and governance, working to ensure that AI development is secure and broadly beneficial.