Lead, Agentic AI Risk Modelling & Mitigations

Greenhouse Software, Inc.; Greater London; Hybrid; GBP 65,000 - 145,000; Full time

Benefits offered by this job

Learning & development stipend

Hybrid working support

25+ days leave & volunteering days

Pension contribution 28.97%

Parental leave

Job summary

AI Security Institute in London is seeking a Workstream Lead to guide the Agentic AI Risk Modelling and Mitigations team. You will shape the research agenda, set scientific direction, and ensure concrete mitigations are adopted by relevant UK organisations.

You will manage a multidisciplinary team, build senior stakeholder relationships, and drive impactful research at the forefront of frontier AI safety and governance.

Qualifications

• 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 clearly to both technical and non-technical audiences.
• 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.

Responsibilities

• 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 AISI research leaders on priorities, quality and delivery across the Research Unit.

Skills

Leadership

Strategic judgement

Research agenda

Translate findings

Team leadership

Stakeholder relations

Communication skills

AI control / safety

Frontier AI timelines

Mitigations design

multidisciplinary collaboration

Job description

AI Security Institute in London is seeking a Workstream Lead to guide the Agentic AI Risk Modelling and Mitigations team. You will shape the research agenda, set scientific direction, and ensure concrete mitigations are adopted by relevant UK organisations.

You will manage a multidisciplinary team, build senior stakeholder relationships, and drive impactful research at the forefront of frontier AI safety and governance.