Agentic AI Risk Modelling and Mitigations

The deadline for applying to this role is Sunday8March 2026 end of day anywhere on Earth.

Team Description

As AI systems grow more capable and autonomous understanding how humans could lose the ability to oversee correct or shut down these systems becomes critical as does identifying what we can do to prevent it. Risk models for AI agents (for example loss of control risk models) remain far less developed than those in comparable domains like cybersecurity and chem-bio and practical mitigations remain underexplored (especially beyond traditionalalignmentandcontrolwork).

AISI is building a new team to close this gap. The new Agentic AI Risk Modelling and Mitigations team will develop rigorous models of how agentic AI could cause harm identifying practical mitigations with a focus on measures the UK government are well-placed to implement. We will draw on expertise only available within government especially the national security community to develop risk models and mitigations far more developed than those in academia or industry.

The hiring manager for this role is Benjamin Hilton; the team is advised byGeoffrey Irving.Youllcollaborate closely with researchers across AISIs red teams evaluation teams and alignment team as well as with government stakeholders.

Relatedpreviouspublications from AISI includetheInternational AI Safety Report theFrontier AI Trends Report as well as:adapting vulnerability disclosure for AI safeguardssafety cases for cyber misuse risk from frontier AI asketch of an AI control safety case analignment safety case sketch based on debate andevaluations of autonomous replication capabilities.

Role Description

Your work willdraw onempirical evidence from AISIs evaluations alongsidethe broadercybersecurity and MLliteratureto develop detailed and precise threat models and to reason carefully about complex and uncertain scenarios and communicate findings clearly to both technical researchers and policy decision-makers. Some projects may also involve hands-on MLor cybersecurity work in collaboration with government partners to develop mitigations.

We are open to hires at junior seniorstaff and principal research scientist may also make an offer to particularly promising candidates with management experience to lead the workstream in a management role.

Representative projects you might work on

• Developing detailed models of specific loss-of-control scenarios such as deceptive alignment duringinternaldeploymentor a long-horizon agentic cyberattack specifying their causal structure key assumptions and plausibility given current and projected AI capabilitiesand propensities.

• Translating risk modelsand associated uncertaintiesinto specifications for AISIs red teams and evaluation teams identifyingthe tests that would provide the most informative evidence about whether specific risk pathways areviable.

• Analysing the effectiveness of mitigations such as monitoring infrastructure compute governancedeploymentguidelines or containment protocols drawing on input from national securitystakeholders andassessing which risk pathwaysremainplausible once mitigations are in place.

• Collaborating and communicating withgovernment and national security stakeholders to develop and implementpossible interventions in parti.

Whatwerelooking for

In accordance withtheCivil Service Commissionrules the following listcontainsall selection criteria for the interview process.

Required experience

The experiences listed below should be interpreted as examples of theexpertisewerelooking for as opposed to a list of everything we expect to find in one applicant:

You may be a good fit if youhave:

• Experience producing detailed threat models risk analyses safety cases or similar structured analytical work in AI safety cybersecurity national security or another domain.

• A track recordof published research or substantial written analysisdemonstratingrigorous reasoning about complex uncertain topics.

• Strong written communication: an ability to present complex technical arguments clearly to both technical and non-technical audiences.

• Deep familiarity withcybersecurity and the ways in which it will beimpactedby high-capability AI agents; alternatively withthe AI alignment and AI safety literature including existing work on loss of controldeception power-seeking scalable oversight and AI control.

• A sense of mission urgency and responsibility for success.

• An ability to bring your own research ideas and work in a self-directed way while also collaborating effectively and prioritising team efforts over extensive solo work.

Strong candidates may also have:

• Hands-on experience with large language models (e.g. training fine-tuning evaluation orred-teaming) providing concrete understanding of current model capabilities and limitations.

• Familiarity with AI capability evaluations and benchmarking methodologies.

• Desire to(and experience with)improveteams through mentoring and feedback.

Security clearance

Wehave a preference forcandidates eligible for UKgovernment SC clearancewhich typically requires residence in the may alsobe requiredto undergo Developed Vetting (DV). DV typicallyrequiresa longer period of UK residency (around5years).

Other core requirements

• You should be able to spend at least 9 days per fortnight working with us.

• You should be willing to work from our office in London (Whitehall) at least 3 days/week.

• You should be UK-based.

What We Offer

Impact you couldnt have anywhere else

• Incredibly talented mission-driven and supportive colleagues.
• Direct influence on how frontier AI is governed and deployed globally.
• Work with the Prime Ministers 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 AI research and adjacent sciences.

Growth & autonomy

• If youre talented and driven youll own important problems early.
• 5 days off learning and development annual stipends for learning and development and funding 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 (cafes food court gym) or 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-wide breaks and 3 days off for volunteering.
• Generous paid parental leave (36 weeks of UK statutory leave shared between parents 3 extra paid weeks option for additional unpaid 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

We are hiring individuals at all ranges of seniority and experience within this research unit and this advert allows you to apply for any of the roles within this range. Your dedicated talent partner will work with you as you move through our assessment process to explain our internal benchmarking process. The full range of salaries are available below salaries comprise of a base salary technical allowance plusadditional benefitsas detailed on this page.

• Level 3 - Total Package 65000 - 75000inclusiveof a base salary 35720 plus additional technical talent allowance of between 29280 - 39280

• Level 4 - Total Package 85000 - 95000inclusiveof a base salary 42495 plus additional technical talent allowance of between 42505 - 52505

• Level 5 - Total Package 105000 - 115000inclusiveof a base salary 55805 plus additional technical talent allowance of between 49195 - 59195

• Level 6 - Total Package 125000 - 135000inclusiveof a base salary 68770 plus additional technical talent allowance of between 56230 - 66230

• Level 7 - Total Package 145000inclusiveof a base salary 68770 plus additional technical talent allowance of 76230