The Role
We are looking for an AI Security Research Engineer to join The Alan Turing Institute s Defence and National Security team, helping to bridge the gap between cutting:edge research and robust technical delivery. This role will focus on designing and running rigorous, reproducible experiments, building high:quality prototypes and research tooling, and evaluating AI systems for security, robustness, reliability and adversarial behaviour. Working closely with researchers and external partners, the postholder will combine strong software engineering skills with curiosity about how modern AI systems behave under stress, helping turn innovative ideas into reliable, extensible technical solutions with real:world impact.
Your Profile
We re looking for a technically strong and rigorous research engineer who combines excellent software engineering fundamentals with a real interest in how modern AI systems behave in practice, particularly under stress, attack or failure conditions. The ideal candidate will be confident working with programming languages used in data science, experienced in structuring and analysing research data or computational experiments, and comfortable operating both independently and collaboratively in a research:driven environment. They will care about clean, well:tested, reproducible work, communicate effectively with both technical and non:technical audiences, and bring a thoughtful, problem:solving mindset to real:world security challenges. Experience in deep learning, interpretability, AI security, red teaming or cybersecurity would be beneficial, but the strongest fit is someone with solid technical foundations, curiosity, and the ability to turn ideas into reliable technical outputs. Eligibility for DV clearance is essential.
How Youll Make an Impact Co:design experiments with researchers, ensuring methodological rigour, appropriate controls, robust evaluation design, and reproducibility. Prototype new ideas quickly and robustly, developing research code that is clean, traceable, and ready for iteration and extension. Adapt, assess, and extend existing research (from within the Institute and beyond) to understand how it behaves in realistic settings. Evaluate models for robustness, security and reliability : including adversarial behaviour, red teaming performance, interpretability signals, and other security relevant properties. Design and develop experimental infrastructure, including pipelines for training, evaluation, adversarial testing, and automated results tracking. Ensure reproducibility and scientific rigour, using strong software engineering practices: testing, version control, CI, environment management, and documentation. Work across disciplines to turn research findings into shareable artefacts and early:stage capabilities for partners. Communicate clearly with researchers, engineers, and operational stakeholders through demonstrations, documentation, and technical discussions. Able to communicate clearly with both technical and non:technical stakeholders and across disciplines with colleagues Application Procedure
If you are interested in this opportunity, please click the apply button below. You will need to register on the applicant portal and complete the application form including your CV (maximum 3 pages, no photo) and covering letter (maximum 2 pages).
As this role requires eligibility for Developed Vetting (DV) clearance, it is an essential part of the application process that you include the following information as part of your cover letter: Your current nationality Your nationality at birth Other nationality (include dual nationality if applicable) Confirmation that you have been residing in the UK for the past 5 years (if you haven t, please provide details of when and where you resided and the reason) Country where you were born. County in which you were born. Town where you were born. Please note, if these details are not provided, we will be una