Cybersecurity Consultant – LLM Red‑Teamer (Remote)

About the role

We are seeking a Cybersecurity Consultant to act as an LLM Red‑Teamer on a contract basis. The specialist will probe large language models for weaknesses such as bias, toxicity, factual errors and jailbreak vulnerabilities, helping a global technology leader deliver safer AI products.

Key responsibilities

• Design and execute red‑teaming strategies that uncover security and ethical flaws in LLM outputs.
• Build automated and manual testing frameworks to simulate adversarial attacks, including prompt injection and jailbreak techniques.
• Document findings in structured reports, assess risk, and propose concrete mitigations.
• Collaborate with AI safety researchers to refine testing protocols and stay aligned with emerging threats.
• Continuously monitor advances in AI security, prompt engineering and responsible AI guidelines.

Required profile

• Proven experience in adversarial testing of large language models.
• Strong programming skills in Python and familiarity with AI/ML libraries such as Hugging Face or PyTorch.
• Solid understanding of cybersecurity principles as they apply to AI systems.
• Ability to analyze model outputs for bias, toxicity, and hallucinations.
• Excellent written communication for clear vulnerability reporting.

Required skills

• Python programming
• Hugging Face library
• PyTorch framework
• Adversarial testing of LLMs
• Prompt engineering and injection techniques

What we offer

• Contract position with a competitive rate of $40‑$65 per hour.
• Fully remote work, allowing you to operate from anywhere.
• Opportunity to influence the security posture of cutting‑edge AI products at a leading tech company.