UK AI Security Institute Hires Research Engineers for Alignment Red Team
birchlse · x · 2026-09-29
The UK AI Security Institute's Alignment Red Team is hiring Research Engineers/Scientists in London, with applications open until October 11, 2026.
The team specializes in detecting and evaluating misalignment in frontier AI systems—deceptive alignment, research sabotage, reward-seeking—through novel research and pre-/post-deployment evaluations. Findings are shared with frontier labs and allied governments to improve alignment training and monitoring. AISI describes itself as the world's largest and best-funded team for advanced AI risk, based in the heart of the UK government with direct lines to No. 10.
More from Safety
- The AI training trilemma: hack-proof training, useful evals, no incidents — pick two — davidmanheim · 2026-09-29
- ImageMagick 7.1.2 RCE: crafted image dimensions chained to heap overflow and system() — evilsocket · 2026-09-29
- Micah Carroll backs safety cases as a north star for risk-informed model development — EvanHub · 2026-09-29
- Imprint Reader Decodes Weight Updates into Natural Language, Enables Targeted Edits — Guanxu Chen · 2026-09-29
- When Do Model Internals Help? Benchmarking Representation Engineering for LLM Safety — Tianyi Guan · 2026-09-29
- Neural Watermarks Can Be Forged via Residual Transfer; Paper Pinpoints Architectural Root Cause — Ziping Dong · 2026-09-29