AI Security & Control Researcher

Location: In-person role based in the London or San Francisco office, with some work-from-home arrangements. Visa sponsorship is available in both the UK and US.

Salary: £135,000–£200,000 per year, approximately $180,000–$270,000.

Company

hirify.global studies AI loss-of-control risks, develops scheming detection and control research, and builds Watcher, a security product for coding-agent deployments.

What you will do

• Develop threat models, kill chains, security levels, and failure-mode libraries for potentially misaligned or compromised coding agents.
• Design realistic attack trajectories and exploits for monitor development, backtesting, and adversarial test suites.
• Adjudicate flagged agent trajectories and use findings to improve monitors and control policies.
• Red-team Watcher, define product security priorities, and advise on enterprise security buyer requirements.
• Own application-security standards, vendor security decisions, attack-surface reduction, cloud and deployment security, and isolation controls.
• Define requirements for tenant isolation, encryption, access control, data retention, product threat modeling, and incident response.

Requirements

• 5+ years of hands-on technical security experience, excluding purely GRC or compliance work.
• Ability to read code, understand infrastructure, evaluate technical controls, and build custom security solutions.
• Direct experience with application, cloud, or product security, ideally involving sensitive customer data.
• Strong understanding of enterprise security buyers and the ability to work across hands-on security and product strategy.
• Strong written communication for threat models, security documentation, questionnaires, and customer-facing materials.
• Ability to work in person from the London or San Francisco office.

Nice to have

• AI/ML, LLM security, or AI control research experience.
• Detection engineering, SOC, incident analysis, insider threat, or offensive security experience.
• Experience building security products or working at a security vendor.
• Formal AI safety research experience.

Culture & Benefits

• Flexible working hours and schedule with some work-from-home arrangements.
• Unlimited vacation and sick leave.
• Up to six months of paid parental leave.
• Comprehensive health, dental, and vision insurance, plus retirement savings with employer matching.
• Paid work trips, staff retreats, relevant conferences, provided meals on workdays, and a $1,000 annual professional development budget.
• Equity, competitive benefits, and relocation support with visa fees where applicable.

Hiring process

• Screening interview, three-hour take-home test, three technical interviews, and a final interview with the CEO.
• No general LeetCode-style coding interview; AI tools may be used for the take-home test.