Alignment Red Team Research Engineer Research Scientist
UK government research organisation that evaluates advanced AI risks and develops and tests mitigations to inform governments.
About AI Security Institute
The AI Security Institute (AISI) is a research organisation within the UK Department for Science, Innovation and Technology. It conducts technical research, evaluates leading AI systems, develops risk mitigations, and shares evaluation infrastructure such as Inspect.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will research and evaluate misalignment risks in frontier AI systems. You will build alignment evaluations, run pre-deployment testing, analyse and report findings, publish research, and develop software and tooling that improves evaluation quality, realism, and usability.
Requirements
- Autonomous experience delivering complex AI safety, security, or alignment research projects involving engineering, experiment design, and frontier LLM analysis
- Software engineering and machine learning experience
- At least 1 year of professional Python programming experience for machine learning or software engineering
- Experience writing clean, documented machine learning research code
- Experience with PyTorch or Inspect
- Ability to work collaboratively and adapt to team needs
- Familiarity with alignment literature, LLM post-training, loss-of-control risks, and threat models
- Proficient use of LLM coding tools and agents
Responsibilities
- Research methods for automatically identifying misalignment in frontier models
- Build and run alignment evaluations for loss-of-control risks
- Run pre-deployment alignment evaluations and analyse and report results
- Contribute to research publications and technical reports
- Design and build software and open-source tooling for alignment evaluations
- Conduct threat modelling and translate risks into testable hypotheses
- Investigate alignment incidents
- Mentor and advise external collaborators and researchers
Benefits
- Pre-release access to frontier models and ample compute
- Hybrid working and flexibility for occasional remote work abroad
- Stipend for work-from-home equipment
- At least 25 days of annual leave
- 8 public holidays
- Extra team-wide breaks
- 3 days of volunteering leave
- Paid parental leave
- Employer pension contribution of 28.97% of base salary
- Cycling, donation, retail, and gym discounts and benefits
Hiring Process
Initial assessment → initial screening call → technical assessment → research interview → behavioural interview → final interview with senior leadership.
