Research Residency – Red Team
UK government research organisation that evaluates advanced AI risks and develops and tests mitigations to inform governments.
Funding history
Investors
About The AI Security Institute (AISI)
The AI Security Institute is a research organisation within the UK Department for Science, Innovation and Technology. It tests leading AI systems, conducts technical research on advanced-AI risks and solutions, develops evaluation infrastructure, and informs UK and allied-government policy.
Skills
Candidate Availability
About the Role
You will join one of the Red Team sub teams (Alignment, Control or Misuse) as a resident for a default 6-month residency, flexible to shorten or extend. You will work on a defined project with support from an experienced research engineer or scientist, helping design and run attacks and evaluations on frontier AI systems to find weaknesses in their safety measures. You will write code and build tools to run experiments at scale, analyse results and turn them into clear findings, and keep up with the research literature. Promising residents may be offered a full-time role afterwards.
Requirements
- Currently studying for a PhD, or postdoctoral researcher who submitted PhD within the last 2 years, in machine learning, computer science, computer security or a related field
- Experience running experiments or analysing data
- Good research habits such as reproducibility and honesty about uncertainty
- Clear written and spoken communication
- Ability to obtain BPSS clearance and criminal record check; preference for CTC eligibility
Responsibilities
- Work closely with research scientists to decide which questions matter most and how to test them
- Work on a defined project with support from an experienced research engineer or scientist
- Help design and run attacks and evaluations on frontier AI systems to find weaknesses in safety measures
- Write code and build tools to run experiments at scale with focus on reliability, speed and reproducibility
- Analyse experiment results and turn them into clear findings for technical and policy audiences
- Keep up with new attack techniques and research literature and apply insights to the work
- Learn how frontier AI models are evaluated and red teamed in practice
Benefits
- Pre-release access to frontier models and ample compute
- Annual stipends for learning and development and funding for conferences
- Hybrid working and occasional remote work abroad
- Stipends for work-from-home equipment
- At least 25 days annual leave and 8 public holidays
- 3 days off for volunteering
- Generous paid parental leave
- Civil Service pension with up to 14.75% employer contributions
- Discounts for cycling to work, donations and retail/gyms
Hiring Process
Typical process: initial assessment, initial screening call, technical assessment, research interview, and final interview with members of the senior leadership team. Process may vary by candidate.
