AI Jailbreak & Prompt-Injection Security Specialist (Remote)

About the role

We are seeking an AI Jailbreak & Prompt‑Injection Security Specialist to work on a contract basis. The role focuses on uncovering vulnerabilities in AI models, testing defenses against prompt‑injection attacks, and building robust security frameworks for a global technology leader.

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 AI security mechanisms.
• Document findings and recommend improvements for AI systems.
• Collaborate with cross‑functional teams to embed security best practices into AI 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 frameworks.
• Strong background in adversarial machine learning and ethical hacking.
• 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 programming
• Scripting for automated security testing
• AI security tools and frameworks
• Prompt‑injection testing techniques
• Adversarial machine learning
• Ethical hacking methodologies
• AI model architecture knowledge
• Inference pipeline analysis
• Security log analysis
• Threat modeling
• Risk assessment

What we offer

• Contract role with competitive hourly rate ($50‑$90/hour).
• Fully remote work – work from anywhere.
• Opportunity to impact the security of cutting‑edge AI deployments.
• Collaboration with a global leader in technology, information, and internet services.