AI Jailbreak & Prompt-Injection Security Specialist (Remote)

About the role

We are hiring for a client to work as an AI Jailbreak & Prompt‑Injection Security Specialist on a contract basis. The role focuses on identifying vulnerabilities in AI models, testing defenses against prompt‑injection attacks, and developing robust security frameworks. This is a fully remote position with an hourly rate of $50‑$90.

Key responsibilities

• Conduct deep‑dive analysis of AI model vulnerabilities to prompt‑injection and jailbreak techniques.
• Develop and refine testing methodologies to evaluate the robustness of AI security mechanisms.
• Design and execute jailbreak scenarios to assess model resilience.
• Document findings and recommend security improvements for AI systems.
• Collaborate with cross‑functional teams to integrate security best practices into AI deployment pipelines.
• Stay current with emerging threats in AI security, including new jailbreak and injection vectors.

Required profile

• Experience with AI security, prompt‑injection, and jailbreak testing frameworks.
• Proficiency in Python and scripting for automated security testing.
• Knowledge of adversarial machine learning and ethical hacking techniques.
• Familiarity with AI model architectures and inference pipelines.
• Ability to analyze security logs and interpret model behavior under attack.
• Experience with threat modeling and risk assessment in AI systems.

Required skills

• Python
• Scripting (e.g., Bash, PowerShell)
• AI security testing
• Prompt‑injection testing
• Jailbreak testing frameworks
• Adversarial machine learning
• Ethical hacking
• AI model architecture knowledge
• Inference pipeline analysis
• Security log analysis
• Threat modeling
• Risk assessment

What we offer

• Competitive hourly rate ($50‑$90)
• Fully remote work
• Contract position with a global technology leader
• Opportunity to shape security standards for AI deployments