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 role focuses on uncovering vulnerabilities in large language models, testing defenses against prompt‑injection attacks, and shaping security frameworks for AI deployments.

Key responsibilities

• Conduct deep‑dive analysis of AI model vulnerabilities to prompt‑injection and jailbreak techniques.
• Design and execute jailbreak scenarios to assess model resilience.
• Develop and refine testing methodologies for evaluating AI security mechanisms.
• Document findings and provide actionable recommendations for improving AI system security.
• 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, prompt‑injection, and jailbreak testing frameworks.
• Strong background in 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 for AI systems.

Required skills

• Python
• Scripting (e.g., Bash, PowerShell)
• AI model architectures
• Adversarial machine learning
• Threat modeling
• Risk assessment

What we offer

• Competitive hourly rate of $50‑$90.
• Fully remote work from anywhere.
• Opportunity to influence security of leading AI products.
• Contract engagement with potential for extension.