Cybersecurity Consultant – LLM Red‑Teamer (Remote)

About the role

We are seeking a specialist to join a leading technology client as a Cybersecurity Consultant focused on red‑team testing of large language models. The role is fully remote and contract‑based, offering the chance to influence AI safety before public deployment.

Key responsibilities

• Design and execute red‑team scenarios that expose bias, toxicity, factual errors, and jailbreak vulnerabilities in LLM outputs.
• Build automated and manual testing frameworks to simulate adversarial attacks on AI models.
• Document findings in structured reports, highlighting risks and recommending concrete mitigations.
• Collaborate with AI safety researchers to refine testing protocols and stay ahead of emerging threats.
• Monitor the latest developments in prompt injection, jailbreak techniques, and AI security best practices.

Required profile

• Proven experience in adversarial testing of large language models or similar AI systems.
• Strong background in cybersecurity principles applied to AI.
• Excellent written communication skills for clear vulnerability reporting.
• Familiarity with ethical AI guidelines and responsible development practices.
• Ability to analyze model outputs for bias, toxicity, and hallucinations.

Required skills

• Python programming.
• Experience with AI/ML frameworks such as Hugging Face.
• Experience with PyTorch.

What we offer

• Competitive hourly rate of $40‑$65.
• Opportunity to work with a global leader in technology and AI safety.
• Fully remote work arrangement, allowing flexibility to work from anywhere.