Teams at AI Security Institute

The Chem Bio team researches chemical and biological risks from frontier AI systems. Work includes designing evaluations and benchmarks, capability elicitation, threat modelling, developing safeguards and monitoring tools, building research infrastructure, and translating findings into actionable recommendations for AI developers and government stakeholders.

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.

Lead research programme architecture and delivery for chem-bio AI research: scope ambiguous technical questions into tractable projects, track progress, remove blockers, manage cross‑government technical engagement, and maintain team operational rhythm while balancing security and research agility.