Cybersecurity & AI Red‑Teaming Trainer (Remote, $60‑$70/hr)

About the role

We are looking for experienced cybersecurity and AI red‑team experts to join our AI Labor Marketplace as independent consultants. You will help improve large language models by designing adversarial scenarios, testing model robustness, and documenting vulnerabilities to ensure trustworthy AI systems.

Key responsibilities

• Conduct AI red‑teaming, jailbreak, and prompt‑injection testing.
• Develop adversarial prompts and attack methodologies.
• Evaluate model responses for safety, compliance, and robustness.
• Identify, document, and report vulnerabilities, weaknesses, and failure modes.
• Produce structured analysis reports and rationales.
• Collaborate with project teams through documented findings and recommendations.

Required profile

• Professional experience in cybersecurity, AI safety, or related analytical fields.
• Strong adversarial thinking and problem‑solving abilities.
• U.S. residency and eligibility to work as an independent contractor.
• Availability of 20+ hours per week and ability to start immediately.

Required skills

• Cybersecurity
• AI red‑teaming
• Offensive security
• Penetration testing
• Bug bounty research
• Threat intelligence
• Application security
• Vulnerability research
• AI safety
• LLM evaluation
• Machine Learning/NLP engineering
• Prompt‑injection testing
• Adversarial testing

What we offer

• Hourly rate between $60 and $70.
• Flexible, self‑managed schedule.
• Fully remote work environment.