Research Engineer – Human Influence

AI Security Institute; Greater London; Hybrid; GBP 65,000 - 145,000; Full time

Benefits offered by this job

Pre-release model access

Ample compute

Publication opportunities

Learning stipend

Conference funding

Job summary

AI Security Institute, based in London, seeks a Research Engineer to advance our Human Influence program through scalable RL post-training, evaluation pipelines, and rigorous experimentation on frontier AI safety. You will work alongside researchers and engineers, deploying robust ML systems and contributing to policy-relevant AI governance discussions.

Join a hyper-impactful team with access to pre-release models, ample compute, and opportunities to publish.

Qualifications

• Proven experience deploying a benchmark, evaluation, or product to users.
• Clear understanding of the current AI safety literature, and interest in Human Influence topics.
• Clear and consistent communication.
• Clear understanding of fundamental Machine Learning concepts.

Responsibilities

• Designing and building a Reinforcement Learning environment aimed at mitigating model deception in one-to-one conversations or multi-agent threads.
• Leveraging interpretability methods to identify why models exhibit concerning behavior and designing mitigations.
• Building the scalable system architecture underpinning repeatable delivery and analysis of model evaluations and benchmarks.
• Delivering ambitious, engineering-heavy research projects on Human Influence topics using post-training techniques on large compute clusters.

Skills

Reinforcement Learning

Python

PyTorch

JAX

Keras

Docker

Kubernetes

Tools

Docker

Kubernetes

Ray

FastAPI

SLURM

Job description

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.

We’re here because governments are critical for advanced AI going well, and UK AISI is uniquely positioned to mobilise them. With our resources, unique agility and international influence, this is the best place to shape both AI development and government action.

The deadline for applying to this role is Sunday 11th October 2026, end of day, anywhere on Earth.

Team Description

The Human Influence (HI) team focuses on the ways in which AI can influence human beliefs, decisions, and behaviour. A substantial class of AI risk operates through people. AI systems can persuade people to change their beliefs and to take action; can build trusting relationships with people in order to exploit them; can extract private information from them; and can hold delegated ownership of high-stakes decisions.

Our work is highly interdisciplinary, drawing on methods from computational social science, AI safety and security, cognitive and behavioural science, machine learning, and data science. Typical projects include running rigorous human-AI interaction studies and randomised controlled trials, building evaluations and benchmarks that track AI capabilities across model releases, eliciting model capabilities through fine-tuning and self-play, and developing datasets to monitor real-world risk exposure and severity.

Role Description

We are looking for a Research Engineer to join the Human Influence team . Successful candidates will be strong researchers and engineers with a track record of carrying out scalable work in LLM post-training and fine-tuning , especially with Reinforcement Learning ; or w ith comparable expertise in engineering and validating large-scale evaluation pipelines.

Projects the Research Engineer might deliver include:

• Designing and building a Reinforcement Learning environment a imed at mitigating a model’s ability to e.g. deceive a user i n a one-to-one conversation or within multi-agent threads.
• Leveraging state-of-the-art interpretability methods to iden tify why models exhi bit con cerning behaviour , and designing mitigations that c an be applied to models irrespective of training regime.
• Building the scalable system architecture underpinning the repeatable delivery and analysis of model evaluations and benchmarks.
• Delivering ambitious, engineering-heavy research projects on Human Influence topics, for instance by leveraging post-training techniques on a large compute cluster.

Who we're looking for

This is a multidisciplinary team , and successful candidates come from a wide range of backgrounds.

General:

• Proven experience de ploy ing a benchmark, evaluation, or product to users, e.g. an evaluations pipeline in an app, an open-source contribution, or similar large-scale contributions to research.
• Clear understanding of the current AI safety literature, and an interest in topics relevant to Human Influence .
• Clear and consistent communication .
• Clear understanding of fundamental Machine Learning c o n c epts.

Research and engineering:

• Experience fine-tuning or post-training LLMs using standard methods , using common libraries like PyTorch , Keras , JAX, or custom code.
  
• Comfortable working with RL environments and using RL or other reward-based methods to post-train or finetune an ML model, ideally an LLM .
• Writing scalable and maintainable production code in (at least) Python.
• Comfortabl e with serving, scaling, and containerising ML code , e.g. using Docker, Kubernetes, Ray, FastAPI , SLURM, e specially on large compute clusters.
• Good understanding of model internals, e.g. for mechanistic interpretability research, or analysing model activations and weights
• Experience shipping an AI safety pipeline to production (e.g. evaluations, monitoring, serving custom models), going beyond research prototypes
• Experience using data to answer complex research questions, e.g. by scoping, training, and validating a classifier or finetuned LLM
• Experience with frontend and node.js deployments

What We Offer

Impactyoucouldn'thave anywhere else

• Incredibly talented, mission-drivenand supportive colleagues.
• Direct influence on how frontier AI is governed and deployed globally.
• Work with the Prime Minister’s AI Advisor and leading AI companies.
• Opportunity to shape the first & best-resourced public-interest research team focused on AI security.

Resources & access

• Pre-release access to multiple frontier models and ample compute.
• Extensive operational support so you can focus on research and ship quickly.
• Work with experts across national security, policy, AIresearchand adjacent sciences.
• Ifyou’retalented and driven,you’llown important problems early.
• 5 days offand annual stipends forlearning and development, andfunding for conferences and external collaborations.
• Freedom to pursue research bets without product pressure.
• Opportunities to publish and collaborate externally.

Life & family*

• Modern central London office, or where applicable, 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-widebreaksand 3 days off for volunteering.
• Generous paid parental leave (36 weeks of UK statutory leave shared between parents + 3 extra paid weeks + option foradditionalunpaid 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.
  

*These benefits apply to direct employees. Benefits may differ for individuals joining through other employment arrangements such as secondments.

Annual salary is benchmarked to role scope and relevant experience. Most offers land between £65,000 and £145,000 made up of a base salary plus a technical allowance (take-home salary = base + technical allowance). An additional 28.97% employer pension contribution is paid on the base salary.

This role sits outside of the DDaT pay framework given the scope of this role requires in depth technicalexpertisein frontier AI safety,robustnessand advanced AI architectures.

The full range of salaries are available below:

Additional Information

Use of AI in Applications

Artificial Intelligence can be a useful tool to support your application, however, all examples and statements provided must be truthful, factually accurate and taken directly from your own experience. Where plagiarism has been identified (presenting the ideas and experiences of others, or generated by artificial intelligence, as your own) applications may be withdrawn and internal candidates may be subject to disciplinary action. Please see our candidate guidance for more information on appropriate and inappropriate use.

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.

The Civil Service Code (opens in a new window) sets out the standards of behaviour expected of civil servants.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.