Skip to content
← UK AI Security Institute

Research Residency – Red Team

UK AI Security Institute · London, UK

Research instituteonsiteintern
Apply on the lab’s site ↗

At a glance

Highlights

  • Evaluate safety measures of frontier AI systems shaping global deployment.
  • Stress-test alignment, control and misuse safeguards for advanced models.
  • Share findings directly with leading AI labs, UK officials and allies.

What they offer

  • 6-month residency with flexibility to shorten or extend per availability
  • Potential full-time employee role following end-of-residency review

Ideal candidate

Curious PhD researcher driven by AI safety who enjoys adversarial thinking, hands-on experiments, and turning cutting-edge red-teaming insights into safer real-world AI deployment.

Requirements

  • Currently studying for a PhD or postdoc within 2 years of submission in ML, computer science, security or related field
  • Research experience or familiarity in adversarial ML, AI security, alignment, control or evaluations
  • Experience with optimisation methods such as RL, fine-tuning or evolutionary methods
  • Familiarity with loss-of-control threat models such as deceptive alignment or reward-seeking
  • Hands-on experience red-teaming or jailbreaking AI systems, CTF or bug bounty experience
  • Built evaluations, agents or fine-tuned models with LLMs using PyTorch or Hugging Face
  • Public research or technical work such as papers, preprints, open-source tools or blog posts
hiring process
Apply by end of day 8 December anywhere on Earth; successful candidates complete criminal record check and BPSS clearance with preference for CTC eligibility.

Lab profile

About UK AI Security Institute

UK government institute studying advanced AI risks and turning research into protective action.

Known for

  • Alignment red-teaming
  • Control red-teaming
  • Misuse red-teaming
  • Cyber and autonomous systems security

Key facts

  • Based in the UK
  • UK government-backed
  • World's largest dedicated advanced AI risk team
More about UK AI Security Institute →
Apply on the lab’s site ↗

Posted · Last seen