AI Security Engineer (LLM Red Teaming & Prompt Injection)

About the role

We are looking for an AI Security Engineer specialized in large‑language‑model (LLM) red teaming and prompt injection. You will create, execute, and document test cases that probe AI models for vulnerabilities such as jailbreaks and malicious prompt attacks.

Key responsibilities

• Design and implement prompt‑injection test cases targeting LLMs.
• Run automated and manual attacks against AI models and verify outcomes.
• Document successful exploits and produce clear, reproducible reports.
• Write structured test cases in YAML, JSON, or similar formats.
• Validate security test results and ensure proper remediation guidance.

Required profile

• Professional experience in cyber security, application security, penetration testing, or red teaming.
• 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) and using Docker, Git, command‑line tools, and APIs.
• Familiarity with Python scripting is a plus.
• Background in AI security research, offensive security, bug bounty programs, or ethical hacking is highly preferred.

Required skills

• Cyber security
• Application security
• Penetration testing
• Red teaming
• LLM security
• Prompt injection techniques
• Docker
• Git
• Command‑line tools
• APIs
• Python (optional)
• YAML/JSON test case authoring