Safety Writing Scientist

About the AI Security Institute
The AI Security Institute is the world's largest and best-funded team dedicated to understanding advanced AI risks and translating that knowledge into action. We're in the heart of the UK government with direct lines to No. 10 (the Prime Minister's office), and we work with frontier developers and governments globally.
With our resources, unique agility and international influence, this is the best place to shape both AI development and government action.
The AI Security Institute's Red Team researches these interventions across three sub-teams (misuse, alignment, and control): we evaluate the protections on current frontier AI systems and research what measures could better secure them in the future. We share our findings with frontier AI companies, key UK officials, and other governments in order to inform their respective deployment, research, and policy decision-making.
We have published on several topics, including agent misuse, defending finetuning APIs, third-party attacks on agents, safeguards safety cases, and attacks on layered defenses, a library for running AI control experiments, and pre-deployment testing of misalignment risks. Some example impacts have been advancing the benchmarking of agent misuse, identifying vulnerabilities previously unknown to frontier AI companies, and producing insights into the feasibility and effectiveness of attacks and defences in data poisoning and fine-tuning APIs.
In our team, you can meaningfully advance both research on how to attack and defend frontier AI systems, as well as government understanding of misuse and misalignment risks, which we see as critical to the safe and secure deployment of advanced AI.
We're looking for researchers across our misuse, alignment, and control subteams with expertise developing and analysing attacks and protections for systems based on large language models or who have broader experience with frontier LLM research and development. An ideal candidate would have a strong record of performing and publishing novel and impactful research in these or other areas of LLM research.
We're primarily looking for research scientists, but we can support staff's work spanning or alternating between research and engineering. The broader team's work includes research - like assessing the threats to frontier systems, performing novel adversarial ML research on frontier LLMs, and developing novel attacks - and engineering, such as building infrastructure for running evaluations.
We are open to hires at junior, senior, staff and principal research scientist levels.
Representative projects you might work on
~ Designing, building, running and evaluating methods to automatically attack and evaluate safeguards, such as LLM-automated attacking and direct optimisation approaches.

~ Building a benchmark for asynchronous monitoring for signs of misuse and jailbreak development across multiple model interactions.

~ Investigating novel attacks and defences for data poisoning LLMs with backdoors or other attacker goals.

~ Performing adversarial testing of frontier AI system safeguards and produce reports that are impactful and action-guiding for safeguard developers.

Hands-on research experience with large language models (LLMs) - such as training, fine-tuning, evaluation, or safety research.

~ Ability and experience writing clean, documented research code for machine learning experiments, including experience with ML frameworks like PyTorch or evaluation frameworks like Inspect.

~ An ability to bring your own research ideas and work in a self-directed way, while also collaborating effectively and prioritizing team efforts over extensive solo work.

Extensive experience writing production quality code.

~ Experience designing, shipping, and maintaining complex technical products.

Opportunity to shape the first & best-resourced public-interest research team focused on AI security.

Extensive operational support so you can focus on research and ship quickly.

~ Work with experts across national security, policy, AI research and adjacent sciences.

Freedom to pursue research bets without product pressure.

~ Modern central London office (cafes, food court, gym) or option to work in similar government offices in Birmingham, Cardiff, Darlington, Edinburgh, Salford or Bristol.

~ Hybrid working, flexibility for occasional remote work abroad and stipends for work-from-home equipment.

~ At least 25 days' annual leave, 8 public holidays, extra team-wide breaks and 3 days off for volunteering.

~ Generous paid parental leave (36 weeks of UK statutory leave shared between parents + 3 extra paid weeks + option for additional unpaid time).

~ On top of your salary, we contribute 28.97% of your base salary to your pension.

~ Discounts and benefits for cycling to work, donations and retail/gyms.

*Most offers land between £65,000 and £145,000 (base plus technical allowance), with 28.97% employer pension and other benefits on top.
Level 3: £65,000-£75,000 (Base £35,720 + Technical Allowance £29,280-£39,280)

~ Level 4: £85,000-£95,000 (Base £42,495 + Technical Allowance £42,505-£52,505)

~ Level 5: £105,000-£115,000 (Base £55,805 + Technical Allowance £49,195-£59,195)

Level 6: £125,000-£135,000 (Base £68,770 + Technical Allowance £56,230-£66,230)
Level 7: £145,000 (Base £68,770 + Technical Allowance £76,230)
Research interview

~ 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. The Cabinet Office then processes this data and discloses a limited dataset back to DLUHC as a participating government organisations. In this way, the policy is ensured and the repetition of internal fraud is prevented. For more information please see - Internal Fraud Register.
Successful candidates must undergo a criminal record check and get baseline personnel security standard (BPSS) clearance before they can be appointed. The Civil Service embraces diversity and promotes equal opportunities. As such, we run a Disability Confident Scheme (DCS) for candidates with disabilities who meet the minimum selection criteria. The Civil Service also offers a Redeployment Interview Scheme to civil servants who are at risk of redundancy, and who meet the minimum requirements for the advertised vacancy.
Diversity and Inclusion
The Civil Service is committed to attract, retain and invest in talent wherever it is found. To learn more please see the Civil Service People Plan (opens in a new window) and the Civil Service Diversity and Inclusion Strategy (opens in a new window).