Senior AI Security Researcher

About the role

Refractal is an AI security company building the infrastructure organisations need to defend against autonomous AI threats. It works with governments and organisations that cannot afford to get security wrong, and is growing its team. You will lead offensive security research against AI agents and their infrastructure, and work with engineers to turn your findings into detections, evaluations and defences in the product.

Key responsibilities

• Red-team AI agents across browser, code, enterprise and multi-agent environments
• Research prompt injection, tool abuse, memory poisoning, identity and data-exfiltration attack chains
• Build automated attack tooling and reusable evaluation suites that run in CI and for customers
• Turn findings into detection rules, classifiers and policy controls with engineers
• Lead customer assessments and write findings that security leaders can act on

Required profile

• 6+ years in offensive security, application security, red teaming or vulnerability research
• A record of original findings such as CVEs, bug bounties, published research or conference talks
• Hands-on experience attacking LLM applications or agents, including tool calling, retrieval, memory and permissions
• Clear communication of rigorous findings to engineers and executives

Required skills

• Strong Python and a systems language, with a habit of building your own tooling
• Nice to have: working knowledge of MITRE ATLAS or the OWASP Top 10 for LLM applications
• Nice to have: Montenegrin, Serbian, Bosnian or Croatian

What we offer

• Salary of 40,000 to 95,000 EUR gross per year
• Equity, pension contribution, private medical and dental cover
• Visa and relocation support