AI Security Institute

About the AI Security Institute The AI Security Institute is the world's largest and best-funded team dedicated to understanding advanced AI risks and translating that knowledge into action. We’re in the heart of the…

Agentic AI AI AWS Cloud Kubernetes +8 skills

6 days ago

Alignment Red Team - Research Engineer/Research Scientist

Open 41d HybridUK

United Kingdom

Research Engineer/Scientist on the UK AI Security Institute's Alignment Red Team: researching and running pre-deployment evaluations to detect misalignment in frontier LLMs (deceptive alignment, reward-seeking, research sabotage), and building evaluation software and tooling. Core stack is Python with ML/eval frameworks like PyTorch and Inspect; findings are shared with frontier labs and governmen

AI Anthropic Incident Investigation LLM Machine Learning +4 skills

65K – 145K £

AI Security Institute

2 weeks ago

Senior Software Engineer, Chem-Bio

Open 132d HybridUKSenior

United Kingdom

Senior engineer builds and maintains the shared platform and tooling that chem-bio researchers use to run experiments and ship results, primarily in Python on AWS and Kubernetes.

AI API AWS CI/CD Cloud +9 skills

65K – 145K £

AI Security Institute

2 weeks ago

Technical Programme Manager - Model Transparency

HybridUK

United Kingdom

A Technical Programme Manager for the UK AI Security Institute's Model Transparency team, turning open-ended frontier-AI research questions into tractable, well-sequenced programmes; tracking delivery, unblocking researchers, and engaging technically with government partners. Work blends programme management, frontier AI fluency, and modern productivity tooling in a government AI-safety research s

AI Anthropic Machine Learning OpenAI Slack +2 skills

65K – 145K £

Open positions

Offensive Security Engineer

Alignment Red Team - Research Engineer/Research Scientist

Senior Software Engineer, Chem-Bio

Technical Programme Manager - Model Transparency