About the AI Security Institute
The AI Security Institute is the largest team in a government dedicated to understanding AI capabilities and risks in the world.
Our mission is to equip governments with an empirical understanding of the safety of advanced AI systems. We conduct research to understand the capabilities and impacts of advanced AI and develop and test risk mitigations. We focus on risks with security implications, including the potential of AI to assist with the development of chemical and biological weapons, how it can be used to carry out cyber-attacks, enable crimes such as fraud, and the possibility of loss of control.
The risks from AI are not sci-fi, they are urgent. By combining the agility of a tech start-up with the expertise and mission-driven focus of government, we’re building a unique and innovative organisation to prevent AI’s harms from impeding its potential.
Criminal Misuse Research Scientist
The AI Safety Institute research unit is looking for an exceptionally motivated and talented Research Scientist to work on our Criminal Misuse team.
Criminal Misuse
The Criminal Misuse team seeks to understand how highly capable AI systems can be misused by criminals or people wishing to cause disruption to society. The team is responsible for developing threat models that the potentially undesirable outcomes that could arise from criminal misuse of frontier AI. Additionally, the team conducts research that studies vulnerabilities to criminal misuse from AI systems already in deployment as well as those soon to be deployed and seeks to develop potential mitigations.
Criminal Misuse is a strongly collaborative research team, led by the Societal Impacts Research Director, Professor Christopher Summerfield. Within this role, you will also have the opportunity to regularly interact with our highly talented and experienced staff across the Institute (including alumni from Anthropic, DeepMind, OpenAI, and ML professors from the Universities of Oxford and Cambridge), as well as with other partners from across government.
Person Specification
We are seeking a talented and ambitious Research Scientist who excited about developing and implementing our research vision for this team. The successful candidate will have strong technical skills, including experience with Frontier AI systems, a visible research track record, and a demonstrable interest in AI Safety. Ideally, the candidate will also have experience in studying the potential misuse of Frontier AI systems, including by criminals, terrorists or other organised groups, or a track record of research relating to understanding the use of AI for topics like financial fraud, scams, influence operations, or radicalisation.
In this role, you will need work effectively within a team and will be expected to contribute to broader discussions about goals and strategy. However, you will be expected to be self-driven, to champion your own projects, to define the most important questions to answer, and to design and implement those experiments with the support of software engineers, data scientists and delivery staff. The Research Scientist should be prepared not only to lead research projects, but also to present them in a compelling way to decision-makers so that they create real impact. We would be particularly excited to hear from people who have the following skills and experience:
Required Skills and Experience
- Demonstrable interest in AI Safety, and especially misuse of AI
- Previous research experience with frontier AI systems (such as fine-tuning AI models)
- Strong research experience in Computer Science, AI, or a related field (PhD-level or equivalent), including in experimental design and research problem selection
- A track record of writing production quality code efficiently, especially using Python
- Strong quantitative and statistical skills
- Excellent verbal communication skills across technical and non-technical audiences
- Published and/or forthcoming work on research topics relevant to the role (e.g., AI’s impact on society, multimodal AI, AI and criminal misuse)
- Demonstrable experience of running research experiments involving AI models and/ or human participants
- A collaborative approach to work, and experience of multi-disciplinary teamwork
Desired Skills and Experience
- Experience of running AI capability evaluations
- Research or technical experience with multimodal AI – in particular, audio and video
- A background in research relating to the (criminal) misuse of AI systems
- Experience of utilising public sector datasets
Salary & Benefits
We are hiring individuals at all ranges of seniority and experience. Your dedicated talent partner will work with you as you move through our assessment process to explain our internal benchmarking process. The full range of salaries are available below, salaries comprise of a base salary, technical allowance plus additional benefits as detailed on this page.
- Level 3 - Total Package £65,000 - £75,000 inclusive of a base salary £35,720 plus additional technical talent allowance of between £29,280 - £39,280
- Level 4 - Total Package £85,000 - £95,000 inclusive of a base salary £42,495 plus additional technical talent allowance of between £42,505 - £52,505
- Level 5 - Total Package £105,000 - £115,000 inclusive of a base salary £55,805 plus additional technical talent allowance of between £49,195 - £59,195
- Level 6 - Total Package £125,000 - £135,000 inclusive of a base salary £68,770 plus additional technical talent allowance of between £56,230 - £66,230
- Level 7 - Total Package £145,000 inclusive of a base salary £68,770 plus additional technical talent allowance of £76,230
This role sits outside of the DDaT pay framework given the scope of this role requires in depth technical expertise in frontier AI safety, robustness and advanced AI architectures.
There are a range of pension options available which can be found through the Civil Service website.
Selection Process
Additional Information
Internal Fraud Database
The Internal Fraud function of the Fraud, Error, Debt and Grants Function at the Cabinet Office processes details of civil servants who have been dismissed for committing internal fraud, or who would have been dismissed had they not resigned. The Cabinet Office receives the details from participating government organisations of civil servants who have been dismissed, or who would have been dismissed had they not resigned, for internal fraud. In instances such as this, civil servants are then banned for 5 years from further employment in the civil service. The Cabinet Office then processes this data and discloses a limited dataset back to DLUHC as a participating government organisations. DLUHC then carry out the pre employment checks so as to detect instances where known fraudsters are attempting to reapply for roles in the civil service. In this way, the policy is ensured and the repetition of internal fraud is prevented. For more information please see - Internal Fraud Register.
Security
Successful candidates must undergo a criminal record check and get baseline personnel security standard (BPSS) clearance before they can be appointed. Additionally, there is a strong preference for eligibility for counter-terrorist check (CTC) clearance. Some roles may require higher levels of clearance, and we will state this by exception in the job advertisement. See our vetting charter here.
Nationality requirements
We may be able to offer roles to applicant from any nationality or background. As such we encourage you to apply even if you do not meet the standard nationality requirements (opens in a new window).
