AI Security Engineer (LLM Red Teaming & Prompt Injection)

About the role

We are seeking an AI Security Engineer who will focus on LLM red‑team activities and prompt‑injection testing. The role involves creating, executing and documenting security test cases for advanced AI models.

Key responsibilities

• Create prompt‑injection test cases in structured formats such as YAML or JSON.
• Run the test cases against AI models to evaluate vulnerability and verify outcomes.
• Document successful results and any identified weaknesses in clear reports.
• Collaborate with engineering teams to reproduce and remediate discovered issues.

Required profile

• Experience in cyber security, application security, penetration testing or red‑team engagements.
• Strong understanding of LLM security, including prompt injection, jailbreaks and AI attack techniques.
• Ability to design and test prompt‑injection attacks against AI models.
• Experience writing structured test cases (YAML, JSON or similar).
• Background in AI security, LLM security research, offensive security, bug bounty or ethical hacking is highly preferred.

Required skills

• Docker
• Git
• Command‑line tools
• APIs
• Python scripting
• YAML
• JSON