Security Engineer (AI Red Team)

About the role

Refractal is seeking a Security Engineer to join their AI Red Team to test how deployed AI systems and agents fail under adversarial pressure. You will conduct controlled security assessments, document findings, and collaborate with engineering and research teams to develop stronger defenses and repeatable tests. This role focuses on modernizing security to mitigate AI-enabled threats for high-stakes organizations.

Responsibilities

• Design and execute assessments of AI applications and agents, grounded in realistic attacker goals and clearly defined test scope.
• Test realistic threats such as indirect prompt injection, misuse of connected tools, sensitive data exposure and attempts to cross permission boundaries.
• Build reproducible test cases and small testing tools that demonstrate security impact and distinguish reliable failures from one-off outputs.
• Analyse how model behaviour, application design, identity and permissions combine to create vulnerabilities.
• Document findings, recommend practical mitigations and retest fixes with the engineers responsible for the affected systems.

Required skills

• Offensive security
• Application security
• Adversarial testing
• Web applications
• APIs
• Authentication
• Authorisation
• Security failure modes
• AI applications
• Prompt engineering

Nice to have

• LLM applications
• Agent workflows
• Security evaluation suites
• Cloud security
• Identity security
• Infrastructure security

Benefits

• Competitive equity
• Pension contribution
• Private medical cover
• Private dental cover
• Visa support
• Relocation support

About the Company

Refractal is an AI security company building infrastructure to defend against autonomous AI threats. Founded on cybersecurity and AI expertise from MIT, Microsoft, NASA and the U.S. Navy, the company provides solutions to detect AI-enabled threats for governments and organizations.