Founding AI Security Researcher

Refractal; Greater London; On-site; GBP 90,000 - 140,000; Full time

Benefits offered by this job

Equity (founding)

Performance bonus

UK visa sponsorship

Job summary

Refractal in London seeks a founding AI Security Engineer/Researcher to break agentic systems, develop repeatable evaluations, and shape our security roadmap. You will work directly with the founders and early customers, turning insights into production safeguards and policy controls.

You will build exploit chains, automate adversarial testing, and contribute to public research while growing into senior technical leadership. Visa sponsorship and equity accompany a competitive package.

Qualifications

• Strong technical foundation in Security, Computer Science, Machine Learning, or a related field.
• Hands‑on experience in at least one relevant security discipline such as Application Security, Offensive Security, Exploit Development, Cloud Security, Product Security, or AI Red Teaming.
• Ability to build security tooling and proof‑of‑concept exploits, ideally using Python and one or more systems languages.
• Practical understanding of modern LLM and agent architectures, including tool calling, harnesses, retrieval, memory, orchestration, and permission models.
• Familiarity with prompt injection and the ways untrusted content can influence tool‑using AI systems.
• Strong experimental discipline: you can distinguish a compelling demonstration from a reproducible security finding.
• Ability to work independently, communicate clearly, and take ownership of technically ambiguous problems.

Responsibilities

• Break agentic systems before adversaries do, turning findings into repeatable evaluations and production security controls.
• Collaborate with founders and early customers to influence product roadmap.
• Develop exploit chains across model, application, identity, tool, and infra layers.
• Build automated adversarial testing infrastructure and reusable security test suites.
• Threat-model agentic architectures including prompts, tools, memory, and permissions.
• Turn research into detections, runtime evidence, and product requirements.
• Engage with customers to assess deployments and communicate rigorous findings.
• Contribute to public research and responsible disclosure where appropriate.
• Help define Refractal’s security research methodology and grow the security red team.

Skills

Security

Adversarial mindset

LLM architectures

Python

Systems languages

Independent work

Education

Strong technical foundation in Security/CS/ML or related field

Tools

Python

C/C++

Job description

Refractal in London seeks a founding AI Security Engineer/Researcher to break agentic systems, develop repeatable evaluations, and shape our security roadmap. You will work directly with the founders and early customers, turning insights into production safeguards and policy controls.

You will build exploit chains, automate adversarial testing, and contribute to public research while growing into senior technical leadership. Visa sponsorship and equity accompany a competitive package.