Security Specialist – AI Jailbreak & Prompt‑Injection Expert (Remote)

About the role

We are seeking a Security Specialist to help a global technology leader protect its AI models from jailbreak and prompt‑injection attacks. This contract position is fully remote and focuses on uncovering vulnerabilities, testing defenses, and shaping robust security frameworks for AI deployments.

Key responsibilities

• Conduct deep‑dive analyses of AI model vulnerabilities related 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 mitigation strategies.
• Collaborate with engineering and product teams to embed security best practices into AI deployment pipelines.
• Stay up‑to‑date with emerging AI threat vectors and share insights with the broader security community.

Required profile

• Proven experience in AI security, specifically prompt‑injection and jailbreak testing.
• Strong analytical mindset with the ability to interpret model behavior under attack.
• Experience working in a fast‑paced, cross‑functional environment.

Required skills

• Python programming and scripting for automated security testing.
• Knowledge of adversarial machine‑learning techniques.
• Familiarity with ethical hacking methodologies.
• Understanding of AI model architectures and inference pipelines.
• Threat modeling and risk assessment for AI systems.

What we offer

• Competitive hourly rate of $50‑$90.
• Opportunity to work on cutting‑edge AI security challenges for a leading tech organization.
• Fully remote work arrangement with flexible hours.