AI Jailbreak & Prompt‑Injection Security Specialist (Remote)

About the role

We are seeking an AI Jailbreak & Prompt‑Injection Security Specialist to work remotely on a contract basis. The expert will evaluate AI model resilience, design jailbreak scenarios, and help build robust security frameworks for a global technology leader.

Key responsibilities

• Conduct deep‑dive analysis of AI model vulnerabilities to prompt‑injection and jailbreak techniques.
• Develop and refine testing methodologies for AI security mechanisms.
• Document findings and recommend improvements to AI systems.
• Collaborate with cross‑functional teams to embed security best practices into deployment pipelines.
• Stay current with emerging AI security threats and new attack vectors.

Required profile

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

Required skills

• Python
• Scripting for automated security testing
• AI security frameworks
• Prompt‑injection and jailbreak testing tools
• Adversarial machine learning
• Ethical hacking techniques
• Understanding of AI model architectures and inference pipelines
• Security log analysis
• Threat modeling
• Risk assessment

What we offer

• Competitive hourly rate ($50‑$90/hr)
• Fully remote work from anywhere
• Opportunity to influence security strategy for cutting‑edge AI products
• Collaboration with a global leader in technology, information, and internet services