AI Jailbreak & Prompt‑Injection Security Specialist (Remote)

About the role

We are seeking an AI Jailbreak & Prompt‑Injection Security Specialist to join our client on a contract basis. The role is fully remote and focuses on uncovering vulnerabilities in large language models, testing defenses against prompt‑injection attacks, and building robust security frameworks for AI deployments.

Key responsibilities

• Conduct deep‑dive analysis of AI model vulnerabilities to prompt‑injection and jailbreak techniques.
• Design, implement and execute jailbreak scenarios to evaluate model resilience.
• Develop and refine testing methodologies for AI security mechanisms.
• Document findings, produce detailed reports and recommend security improvements.
• Collaborate with cross‑functional teams to embed security best practices into AI deployment pipelines.
• Stay up‑to‑date with emerging AI security threats and new attack vectors.

Required profile

• Proven experience in AI security, specifically prompt‑injection and jailbreak testing.
• Strong background in adversarial machine learning and ethical hacking.
• Ability to analyse security logs and interpret model behaviour under attack.
• Experience with threat modelling and risk assessment for AI systems.

Required skills

• Python programming and scripting for automated security testing.
• Knowledge of AI model architectures and inference pipelines.
• Familiarity with adversarial machine learning techniques.
• Expertise in threat modelling and risk assessment.
• Security log analysis.

What we offer

• Contract position with a competitive hourly rate of $50‑$90.
• Fully remote work from anywhere.
• Opportunity to influence security practices for a global technology leader.