Head of Strategy and Delivery - Red Team, AI Security Institute

The UK AI Security Institute is the world's largest and best-funded team dedicated to understanding the capabilities and impacts of advanced AI and developing practical risk mitigations. We’re in the heart of the UK government with direct lines to No. 10, 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, agility and international influence, this is the best place to shape both AI development and government action to ensure AI systems are deployed safely and responsibly.  

AISI’s Research Unit is a dynamic blend of technical researchers and delivery staff who work collaboratively to scope and deliver our research projects. Our delivery team members are integral to our success. They are the driving force behind our research, unblocking issues, managing risk, and ensuring our research remains high quality and in line with the standards demanded by AISI and government. They set the conditions for success for our technical teams. We aren’t looking for a project manager, you don’t need to be fully agile, rather a pace setter, fixer, and doer. If you can demonstrate that you have delivered big things in Government and can operate under pressure, then this is the role for you. 

Team Description 

The Red Team conducts cutting-edge research to identify, evaluate and stress test vulnerabilities in frontier AI systems, sharing findings directly with leading AI companies, UK officials and allied governments to inform deployment, research and policy decisions. 

The Red Team is composed of three specialised sub-teams, each tackling a distinct set of challenges. While each sub-team has its own focus, the team works closely together, sharing methodologies, tooling, research insights and findings across the wider Red Team. Many of the most impactful projects draw on expertise from across all three sub-teams, and the team actively encourages collaboration to tackle the most pressing challenges in frontier AI safety and security. 

Alignment 

The Alignment sub-team focuses on detecting, evaluating and understanding misalignment in frontier AI systems. Its work centres on loss-of-control risks, including deceptive alignment, research sabotage and self-exfiltration attempts. The team carries out novel research to develop techniques for finding misalignment, investigates how to attribute misaligned behaviour to more fundamental concerns such as instrumental convergence, and conducts pre- and post-deployment evaluations. It shares findings with frontier AI companies and with the UK and allied governments to inform deployment, research and policymaking, and works directly with safety teams at frontier labs to help improve their alignment training and monitoring methodologies. 

Misuse 

The Misuse sub-team focuses on stress testing frontier AI safeguards for dangerous capabilities, researching novel attack vectors and developing advanced automated attack tooling. Its work probes the robustness of safeguards against real-world threats, helping to identify where frontier systems may be vulnerable to exploitation and where defences need to be strengthened. The team shares findings with frontier AI companies, including Anthropic, OpenAI and DeepMind, as well as with key UK officials and other governments, to inform deployment, research and policy decisions and to support the development of more resilient safeguards across the frontier AI ecosystem. 

Control 

The Control sub-team partners with leading frontier AI companies to stress test control measures designed to prevent AI systems from causing harm. Drawing on techniques from adversarial machine learning, it develops algorithms to uncover a wide range of failures in control measures and uses these findings to assess and strengthen them. These partnerships allow the team to directly influence vital control measures, while its position within government enables it to bring its understanding of the current state of control measures to wider government as critical deployment, research and policy decisions are made. 

In this role, you will work with one of the Deputy Directors for the Research Unit and Red Team Workstream Lead Xander Davies, and you will: 

• Own the end-to-end delivery function for a diverse and fast-growing portfolio of projects across the Red Team. 

You’ll ensure projects are scoped clearly, resourced adequately, and delivered on time to a high standard. 

• Set the rhythm and raise the bar across the Team – driving up ambition, removing blockers, and helping technical teams move faster and more confidently. This includes identifying where teams are stuck, designing interventions, and pushing for clarity and pace. 

• Act as a strategic delivery partner to the Deputy Director and Research Director, helping shape team strategy and translate it into operational plans. You’ll also support engagement with senior stakeholders across government, frontier AI companies, and allied governments, ensuring our work lands and sticks. 

• Coach and lead the Strategy & Delivery Managers, creating an environment of autonomy and stretch. You’ll line manage delivery staff, support their professional growth, and role-model high standards of judgment, prioritisation, and delivery under pressure. 

• Build and improve the delivery infrastructure as we scale – identifying and implementing lightweight systems, norms, and workflows that enable more consistent and effective execution across a growing research organisation. 

• Hold a high bar on quality, communications, and risk management, ensuring that project outputs meet AISI’s standards, that risks are surfaced and managed early, and that delivery plans are transparent and shared across the organisation. 

• Mobilise the team’s work – you will provide thought leadership on key audiences within government and beyond, supporting the team to identify policymakers and external partners who would benefit from understanding the research. You and your Strategy & Delivery team will provide guidance on how to translate technical research into impactful policy advice and operational insight. 

This is a highly hands-on role for someone who thrives on responsibility, pace, and problem-solving – and who wants to help shape a world-leading AI research organisation tackling urgent AI safety and security risks. 

Skills, experience, and qualifications (essential) 

• Experience in project delivery, operations, or project management 

• Experience working in a matrix environment, with multidisciplinary teams 

• Strong ability to manage stakeholders 

• Excellent leadership skills 

• Exceptional organisational skills and a systematic approach to problem-solving and delivery 

• Ability to operate in a dynamic, fast-paced environment 

• Excellent communication skills, both written and verbal 

• Willing to apply for developed vetting clearance 

Skills, experience, and qualifications (desirable) 

• Experience working on AI, or similar emerging technology 

• Experience working with research teams 

• Experience scaling teams and processes 

• Passion for AI safety, security, or frontier AI risks 

Selection Process:

As part of the application process, you will be asked to complete a CV outlining your relevant experience required for the job. Further details around what this will entail are listed on the application form. 

The Team will then sift all applications based on the evidence provided in the CV against the essential criteria outlined in the personal specification. 

Those successful at sift will be invited to attend an interview which will comprehensively assess experience related to the role. 

You will be asked to present on your vision and expected outcomes for the Red Team, followed by Q&A from the panel. 

The specific interview presentation title will be: ‘Please spend 30/45 mins presenting on your strategic vision for the Red Team.’ 

Reasonable Adjustment 

We are proud to be a disability confident leader and we welcome applications from disabled candidates and candidates with long-term conditions.  

Information about the Disability Confident Scheme (DCS) and some examples of adjustments that we offer to disabled candidates and candidates with long-term health conditions during our recruitment process can be found in our DSIT Candidate Guidance.  A DSIT Plain Text Version of the guidance is also available.  

We encourage candidates to discuss their adjustment needs by emailing the job contact which can be found under the contact point for applicants section.  

If you are experiencing accessibility problems with any attachments on this advert, please contact the email address in the 'Contact point for applicants' section.  

If successful and transferring from another Government Department a criminal record check may be carried out. 

New entrants are expected to join on the minimum of the pay band. 

A location based reserve list of successful candidates will be kept for 12 months. Should another role become available within that period you may be offered this position. 

Candidates who meet the minimum benchmark may be placed on a Reserve List for consideration for similar roles, including those at a lower grade. Candidates who narrowly miss the benchmark and are not placed on the Reserve List may still be considered for an offer in a similar role at a lower grade. 

Please note terms and conditions are attached. Please take time to read the document to determine how these may affect you. 

Any move to the Department for Science, Innovation and Technology from another employer will mean you can no longer access childcare vouchers. This includes moves between government departments. You may however be eligible for other government schemes, including Tax Free Childcare; for further information visit the Childcare Choices website.  

DSIT does not normally offer full home working (i.e. working at home); but we do offer a variety of flexible working options (including occasionally working from home).  

DSIT cannot offer Visa sponsorship to candidates through this campaign. DSIT holds a Visa sponsorship licence but this can only be used for certain roles and this campaign does not qualify. 

In order to process applications without delay, we will be sending a Criminal Record Check to Disclosure and Barring Service on your behalf. 

However, we recognise in exceptional circumstances some candidates will want to send their completed forms direct. If you will be doing this, please advise Government Recruitment Service of your intention by emailing Pre-EmploymentChecks.grs@cabinetoffice.gov.uk stating the job reference number in the subject heading.  

Applicants who are successful at interview will be, as part of pre-employment screening, subject to a check on the Internal Fraud Database (IFD). This check will provide information about employees who have been dismissed for fraud or dishonesty offences. This check also applies to employees who resign or otherwise leave before being dismissed for fraud or dishonesty had their employment continued. Any applicant’s details held on the IFD will be refused employment.  

A candidate is not eligible to apply for a role within the Civil Service if the application is made within a 5 year period following a dismissal for carrying out internal fraud against government. 

For further information on National Security Vetting please visit the Demystifying Vetting website.