Frontier AI Cybersecurity Engineer

AI Security Institute; Greater London; Hybrid; GBP 90,000 - 130,000; Full time

Job summary

AI Security Institute seeks exceptional cybersecurity experts to work on frontier AI security. You’ll design cyber ranges, run pre-deployment tests, and validate model behaviours, collaborating with engineers and researchers who prioritise impact and autonomy in a mission-driven setting.

Role offers exposure to world-class evaluations, mentoring, and the chance to influence safety standards for frontier AI. Hybrid work from London with global partnerships and strong government ties.

Qualifications

• Strong Python skills with experience writing scripts for automation or security tooling.
• Proven experience in at least one of the following areas of cybersecurity red-teaming: Penetration testing, Cyber range design, Competing in or designing CTFs, Developing automated security testing tools, Bug bounties, vulnerability research, or exploit discovery and patching.

Responsibilities

• Design cyber ranges and CTF-style challenges for automatically grading AI system performance on cybersecurity tasks.
• Build agentic scaffolding to evaluate frontier models, equipping them with tools such as network packet capture utilities, penetration testing frameworks, and reverse engineering/disassembly tools.
• Design metrics and interpret results of cyber capability evaluations.
• Work alongside other engineers to ensure evaluation environments are robust and scalable.
• Write reports, research papers and blog posts to share findings with stakeholders.

Skills

Python scripting

Cybersecurity red-teaming

Penetration testing

CTF design

Cyber range design

Automated security testing tools

Bug bounty research

Open-source tooling

Tools

Packet capture tooling

Penetration testing frameworks

Reverse engineering tools

Job description

AI Security Institute seeks exceptional cybersecurity experts to work on frontier AI security. You’ll design cyber ranges, run pre-deployment tests, and validate model behaviours, collaborating with engineers and researchers who prioritise impact and autonomy in a mission-driven setting.

Role offers exposure to world-class evaluations, mentoring, and the chance to influence safety standards for frontier AI. Hybrid work from London with global partnerships and strong government ties.