As Refractal’s first dedicated AI security hire, you will break agentic systems before adversaries do. You’ll work across research and offensive engineering to turn findings into production security controls. By red-teaming production AI agents and multi-agent environments, you’ll directly influence how consequential autonomous systems are safely deployed at scale.
Founding AI Security Engineer / Researcher at Refractal
Refractal is building the critical security infrastructure for autonomous AI, and they’re looking for their first Founding AI Security Engineer. Backed by recognition from MIT CSAIL and Google, you’ll work directly with a pedigree team from NASA and Microsoft to break agentic systems before adversaries can. This isn't just about synthetic research; you'll be securing real-world deployments for leading startups and government entities. If you have an adversarial mindset and want to define the security foundations for the next decade of AI, this London-based role offers meaningful equity and the chance to lead a category-defining function.
Want to apply for this role?
Jack finds you jobs at companies like Refractal. Talk to Jack to get considered for roles that fit what you're great at.
Location
London, United Kingdom
Compensation
Not Disclosed
Company
Refractal
Role overview
Refractal is building the security infrastructure for autonomous systems. Our founding team combines technical pedigree from MIT, NASA, and the U.S. military with commercial experience in VC and startups. We are starting with monitoring for employee AI usage. Unlike competitors, we are concentrating on native multimodality across browsers, file systems, and beyond.
Refractal is backed by leading institutional investors including Creator Fund, Eka, and Blue Wire Capital. We have also received compute support from Google Cloud, Microsoft for Startups, as well as being recognised by MIT’s flagship CSAIL AI lab as part of CSAIL Alliances.
What you will do
- Red-team production and pre-production AI agents across browser, code, and enterprise environments to discover novel exploits involving prompt injection and tool abuse.
- Build automated adversarial testing infrastructure, attack agents, and reusable security test suites to evaluate complex agentic architectures and trust relationships.
- Translate security research findings into concrete runtime detections, policy controls, and product requirements that directly influence the Refractal roadmap.
Who this is a fit for
- Demonstrated expertise in offensive security, AI red-teaming, or vulnerability research with an adversarial mindset and a proven ability to build security tools.
- Practical understanding of modern LLM architectures, including tool calling, RAG, and orchestration, alongside proficiency in Python and systems languages.
- Ability to work independently on technically ambiguous problems and communicate rigorous, actionable findings to founders and high-profile customers.
Why this role is remarkable
- Join as the first security hire at an early-stage startup founded by a high-pedigree technical team from MIT, NASA, Microsoft, and government.
- Gain direct access to real, high-consequence AI deployments for leading startups and a European government rather than working in synthetic research environments.
- Build category-defining infrastructure to address emerging threats like multi-agent collusion and agentic data exfiltration that traditional cyber companies cannot solve.
How Jack & Jill work together
I get to know what you’re great at, then find roles you’d never find yourself.Ok, I'll go first. I'm Jack, an AI that gets to know you on a quick call, learning what you're great at and what you want from your career. Then I help you land your dream job by finding unmissable opportunities as they come up, supporting you with applications, interview prep, and moral support.
I recruit from Jack’s network and make the intro when I spot a great match.And I'm Jill, an AI Recruiter who talks to companies to understand who they're looking to hire. Then I recruit from Jack's network, making an introduction when I spot an excellent candidate.
Jack gets to know what you're great at and what you want next, then searches 15 million jobs daily and helps you discover roles at companies like this.
Meet Jack
What happens next?
Jack’s an AI agent for job searching and career coaching. He works for you.
Jill is the AI recruiter working for the company. She recruits from Jack’s network.
If your profile’s a match and Refractal wants to meet, Jill will make the intro. In the meantime, Jack will send you excellent alternatives.