Jobs at AI Security Institute

Design and build reliable systems, manage technical projects, write high-quality Python code, and collaborate with researchers to deliver functional software solutions.

Lead design and interpretation of empirically rigorous evaluations of AI systems on virology-relevant tasks. Translate ambiguous biological risk questions into testable evaluations, analyse results and uncertainties, advise on mitigations and evidence standards, produce briefings for senior decision-makers, and collaborate across researchers, policy, and biosecurity communities to ensure technically rigorous, policy-relevant outcomes.

Develop and maintain research-oriented software and infrastructure for evaluation and model hosting. Implement features for Inspect, support open-weights model hosting, design custom research infrastructure, collaborate with researchers, and debug evaluation systems. Work spans cloud infrastructure, MLOps tooling, and open-source contributions.

The Red Team conducts research to identify vulnerabilities in AI systems, collaborating with AI companies and governments to inform policy and improve safety measures.

Manage and structure complex research programmes in AI security for cyber and autonomous systems. Translate open-ended research questions into deliverable plans, track delivery, remove blockers, engage technical government partners, and set operational rhythms for a high-performing team working on frontier-model evaluations.

Evaluate and test frontier AI models for cybersecurity and autonomy. Build and run realistic evaluations (cyber ranges, CTFs), perform pre-deployment testing, validate novel model behaviours, and collaborate with government, labs, and partners to inform AI risk and governance.