Workstream Lead, Agentic AI Risk Modelling and Mitigations

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.

We're here because governments are critical for advanced AI going well, and UK the company 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 Tuesday 13th October 2026, end of day, anywhere on Earth.Job summary Within the company's Research Unit, the Agentic AI Risk Modelling and Mitigations team studies how advanced AI systems could become difficult to oversee, correct or shut down as they take on longer and more autonomous tasks. The team builds scenario-based risk models that extend published work on AI timelines and systemic risk and uses them to identify practical mitigations such as monitoring infrastructure, deployment guidance and containment protocols. Its analysis has been shared across government and is intended to inform real decisions by the organisations best placed to act.

We are looking for a Workstream Lead to lead and line-manage this team through its next phase. You will shape the team's strategy and research agenda, set the scientific direction of its work, and ensure that promising mitigations move from analysis into adoption. This is a senior leadership role for someone who can combine technical judgement, strategic thinking, delivery focus and strong people leadership in a fast-moving and highly consequential area.

This role sits within the company's Research Unit and reports to a Research Unit Deputy Director.

Job description As Workstream Lead for Agentic AI Risk Modelling and Mitigations, you will provide the scientific, strategic and managerial leadership needed to keep the team at the forefront of this area.

You will be accountable for the team's research agenda and for the routes to implementation of any mitigations it identifies. This includes setting priorities, choosing analytical approaches, reviewing the quality of outputs, and ensuring the work is relevant to the institutions that can act on it. You will also lead and develop a multidisciplinary team, oversee multiple strands of work at once, and build strong relationships with senior policy and technical stakeholders across government, research organisations and frontier AI companies.

The team's aim for March 2027 is for the UK organisations best placed to act to have adopted its existing mitigations, and for newly identified mitigations to move more quickly from research to adoption. You will play a central role in achieving that aim.

Role summary You will:

• Set the team's strategy, quarterly plan and overall research agenda;

• Lead the scientific direction of the team's risk modelling, including selecting approaches, choosing which scenarios to develop, and reviewing outputs;

• Develop analyses of how advanced AI systems could become difficult to oversee, correct or shut down, and identify practical ways to reduce those risks;

• Turn research into assessments, mitigations and implementation pathways, and work with relevant UK organisations to support adoption;

• Hire, line-manage and develop a multidisciplinary team, maintaining high standards across multiple strands of work;

• Build trusted relationships with senior policy and technical staff across government, as well as leaders in research organisations and frontier AI companies;

• Work with other the company research leaders on priorities, quality and delivery across the Research Unit.

Person specification In accordance with the Civil Service Commission rules, the following list contains all selection criteria for the interview process.

Essential criteria

• Experience of leading impactful research, scientific work, or technical programmes relevant to frontier AI, AI safety, AI governance, risk analysis, or a closely related field;

• Strong strategic judgement on advanced AI risks and the ability to identify the most important questions in a fast-moving and uncertain area;

• Experience of setting and delivering research agendas or analytical programmes in technically complex environments;

• Ability to lead high-quality analytical or scientific work, including setting direction, reviewing outputs critically, and maintaining rigorous standards;

• Experience of translating technical or research findings into practical recommendations, operational interventions, or policy-relevant outputs;

• Track record of successfully leading and line-managing high-performing multidisciplinary teams, including developing more junior staff;

• Experience of building effective relationships with senior stakeholders, including in government, academia, industry, or other complex institutional environments;

• Strong written and verbal communication skills, with the ability to communicate complex issues to both technical and non-technical audiences.

Desirable criteria

• Expertise in one or more areas relevant to the team's remit, such as AI control, alignment, model autonomy, scenario analysis, systemic risk, or frontier AI governance;

• Understanding of published work on frontier AI timelines, advanced AI risk, or loss of control;

• Experience designing or evaluating mitigations for high-consequence technical risks;

• Background in machine learning, computer science, engineering, mathematics, economics, public policy, security studies, or another relevant discipline;

• Familiarity with government decision-making, national security, or assurance processes.

What We OfferImpactyou couldn't have 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.

Growth & autonomy

• Ifyou'rtalented 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.

Salary 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 technical expertise in frontier AI safety, robustness and advanced AI architectures.

The full range of salaries are available below:

• Level 3:£65,000-£75,000 (Base £39,850 + Technical Allowance £25,150-£35,150)

• Level 4:£85,000-£95,000 (Base £47,355 + Technical Allowance £37,645-£47,645)

• Level 5:£105,000-£115,000 (Base £61,620 + Technical Allowance £43,380-£53,380)

• Level 6:£125,000-£135,000 (Base £74,605 + Technical Allowance £50,395-£60,395)

• Level 7:£145,000 (Base £74,605 + Technical Allowance £70,395)

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 ourcandidate guidance for more information on appropriate and inappropriate use.
. click apply for full job details