Offensive Security Engineer
Job description
An offensive security engineer role at the AI Security Institute, focused on attacking evaluation sandboxes and research infrastructure and building agent-assisted red-teaming harnesses to test the systems used to evaluate frontier AI models.
At a glance
- Employment
- Full-time · Employee (employment agreement)
- Work mode
- Hybrid
- Pay
- GBP 65,000 – 145,000 / year
- Apply before
- November 15, 2026
What you'll do
- Attacking evaluation sandboxes, including container and VM escape, egress controls, and attacking on the evaluation host from inside the sandbox
- Finding vulnerabilities in Inspect, the open-source evaluation framework, and the infrastructure around it, and coordinating fixes and disclosure with maintainers and downstream users
- Building, operating and maintaining agent-assisted red-teaming harnesses end to end, and running them along with manual testing against every new sandbox and evaluation infrastructure release before evaluations depend on it
- Triaging and proving findings: separating real issues from noise in what the agents find and confirming the real ones with working exploits
- Running agent and human red-teaming against the same targets and feeding what you learn back into the tooling
- Planning and running scoped engagements against cloud, identity, model-access paths and research platform, including joint exercises with the detection team
- Helping to build and harden cyber ranges, reviewing evaluation tasks for realism and scoring, and providing human baselines
- Scoping and reviewing external penetration tests
- Keeping model-assisted offensive work within AISI's internal safety governance and approval processes
- Where appropriate, publishing research, writing blog posts and giving talks on sandbox security and AI-assisted offensive work
What we're looking for
- Substantial hands-on offensive security experience in red teaming, penetration testing, vulnerability research or exploit development, with findings you can talk through in depth
- Depth in at least two of: cloud and infrastructure (AWS preferred); container, VM or sandbox escape; application security; vulnerability research and exploit development
- Strong Python and/or another language such as Go, Rust or C, and a track record of writing tools that other people use and that you maintain
- Experience testing live systems safely
- Clear written and verbal communication, including findings that engineers can act on, and the ability to get issues fixed in teams you don't manage
- A serious interest in where frontier AI is heading, and motivation to help make it safe
- Finding and exploiting vulnerabilities in complex, fast-changing systems
- Building tools that make offensive work repeatable
- Judging which findings are real and worth fixing, including findings from AI agents
- Operating safely and accountably under rules of engagement
Nice to have
- Building or using LLM agents, for security work
- Linux internals, kernel or hypervisor security, and isolation technologies such as Kubernetes, gVisor, Firecracker or Proxmox
- CTF challenge design, cyber range building or offensive training content
- Published CVEs, research, conference talks or open-source security tools
- Coordinated vulnerability disclosure
- ML evaluation frameworks and AI/ML platforms
- Mentoring other engineers and raising the technical level of a team
Your team
Security Engineering
Protects AISI's people, partners, models, data and the research infrastructure that AISI's work depends on; builds secure-by-design platforms, automated governance and intelligence-led detection, and is now building an offensive security team.
Benefits
Modern central London office, or where applicable, option to work in similar government offices in Birmingham, Cardiff, Darlington, Edinburgh, Salford or Bristol
Generous paid parental leave (36 weeks of UK statutory leave shared between parents + 3 extra paid weeks + option for additional unpaid time)
- Direct influence on how frontier AI is governed and deployed globally
- Work with the Prime Minister's AI Advisor and leading AI companies
- 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
- 5 days off and 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
- 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
- 28.97% employer pension contribution on base salary
- Discounts and benefits for cycling to work, donations and retail/gyms
How to get hired
- 1Initial assessment
- 2Initial screening call
- 3Technical assessment
- 4Research interview
- 5Behavioural interview
- 6Final interview with members of the senior leadership team
- 7Security Clearance
Apply
Direct apply at Aisi
Opens the job posting at Aisi
About AI Security Institute
The world's largest and best-funded team dedicated to understanding advanced AI risks and translating that knowledge into action
The AI Security Institute is in the heart of the UK government with direct lines to No. 10 (the Prime Minister's office), and works with frontier developers and governments globally.
Mission
To understand advanced AI risks and translate that knowledge into action, shaping both AI development and government action.
Key facts
- Government / AI safety research
- In the heart of the UK government with direct lines to No. 10 (the Prime Minister's office)
- Works with frontier developers and governments globally
- Building an offensive security team with three roles available