Offensive Security Researcher

The Offensive Security Unit (OSU) forms part of the Government’s wider Laboratory for AI Security Research initiative, which brings together academia, industry, and government to advance UK leadership in AI security research.

Without truly understanding the future of cyber‑attacks we are limited in our ability to defend. OSU will be a dedicated team that will identify, design and assess new AI‑enabled offensive techniques.

As an Offensive Security Researcher, you will investigate how modern AI changes what is possible for cyber adversaries. Working from realistic threat scenarios, you will design and evaluate controlled experiments that explore emerging AI‑enabled offensive techniques before they appear in the wild. Outputs may include experimental designs, prototype implementations, reproducible evaluations, technical reports, demonstrations, and briefings for government partners. All work will be conducted within appropriate legal, ethical and governance frameworks.

• Identify high‑value research questions at the intersection of AI and offensive cyber.
• Translate realistic adversary behaviours into testable hypotheses and experimental designs.
• Co‑design and run rigorous evaluations of AI‑enabled offensive techniques, including where they work, fail, or introduce new risks.
• Develop prototypes and reproducible implementations with Offensive Security Engineers.
• Analyse AI‑altered attack surfaces, including how AI may support discovery, chaining, automation, or amplification of cyber techniques.

• Have strong instincts for adversarial thinking and are curious about how systems can be probed, stressed and exploited.
• Are energised by anticipating where offensive capability is heading, rather than only responding to what already exists.
• Enjoy turning ideas into well‑designed experiments and concrete evidence
  .
• Are comfortable working in ambiguous problem spaces where the right questions are not always obvious.
• Can move fluidly between real‑world scenarios, abstract reasoning and experimental validation
  .
• Are motivated by producing work that has real operational relevance and impact
  .
• Like collaborating across disciplines, particularly with engineers and domain experts.
• Communicate clearly with both technical and non‑technical audiences.
• Produce clear technical evidence through reports, demonstrations and briefings.
• Work closely with government and technical stakeholders to ensure research remains grounded, relevant and actionable.

This full‑time post is offered on a two‑year fixed‑term basis. The annual salary is £45,505‑£51,465 plus excellent benefits, including flexible working, family friendly policies, Employee‑only benefits guide | The Alan Turing Institute.

Eligibility for Developed Vetting (DV) clearance is a requirement for this role. Eligibility criteria and further information on the process can be found on the UK Government security vetting website. Applicants should check if they are eligible for DV clearance before applying to this role.

The Alan Turing Institute is committed to creating an environment where diversity is valued and everyone is treated fairly. We value diversity of background, experience and perspective, and are proud to be an inclusive employer. We warmly encourage applications from all backgrounds, particularly from groups currently under‑represented in our sector. If you feel passionate about this role but don’t meet every single requirement, please apply – we recognise that great candidates may bring strengths beyond the criteria listed.