Control Red Team - Research Engineer/Research Scientist
AI Security Institute · London, UK
Posted 14 days ago
or apply directly on AI Security Institute's site. We never take the application ourselves.
Is this posting real?
- This role has been open
- 14 days AI Security Institute's roles stay open a median of 14 days
- Reposted
- No
- Salary listed
- No 0% of AI Security Institute's roles list one
- Ghost-job risk at AI Security Institute
- moderate 4 stale, 1 reposted of 12 open
- Hiring momentum
- 15 roles opened in the last 90 days ↑ up vs. the prior 90 days
- Last confirmed on the employer's board
- 2026-09-17
Measured from postings appearing on and disappearing from AI Security Institute's own greenhouse board since 2026-08-03. Full hiring picture for AI Security Institute.
About this role
In this role, you'll be part of the Control Red Team at the AI Security Institute, focusing on stress-testing control measures for advanced AI systems. Your work will involve designing and running machine learning experiments to evaluate the efficacy of these controls, conducting security analyses, and producing actionable reports for both companies and government entities. You'll also build experimental pipelines and utilize large language models to enhance your research and evaluations.
- benefits
- 5/5
- freshness
- 4/5
- career value
- 5/5
- role clarity
- 5/5
- pay transparency
- 0/5
Scored from the posting itself — how clearly the role is described, how much it says about pay and benefits, and how recently it was listed. Not a judgement of AI Security Institute as an employer.
What you need
- Demonstrated ability to design, build and run ML experiments on frontier models
- Strong software engineering and ML experience, including writing clean, documented, reusable code for machine learning experiments
- Ability to understand and critique how an experiment supports a safety claim
- Impact-driven mindset and collaborative team player
Nice to have
- Good working model of frontier AI companies' internal deployments
- Exceptional red-teaming mindset
- Experience with ML optimisation
- Strong written communication and argumentation skills
- Experience building or operating ML research infrastructure at a large organisation
What you get
- Impact on frontier AI governance and deployment
- Supportive colleagues
- Pre-release access to multiple frontier models and ample compute
- 5 days off and annual stipends for learning and development
- Hybrid working with flexibility for remote work
- At least 25 days’ annual leave and 8 public holidays
Worth weighing
- No specific salary range provided for the role
- Role involves complex research projects with substantial engineering
- Candidates must undergo a criminal record check and security clearance
- Position is within a government-related organization, which may have additional requirements
Summarised from AI Security Institute's posting. Read the full original.
Listed by AI Security Institute on their greenhouse job board, last confirmed open on 2026-09-17. PitchMeAI is not the employer.