Cybersecurity Consultant – LLM Red‑Teamer (Remote)

About the role

We are seeking a specialist to join a leading technology client on a contract basis as an LLM Red‑Teamer. The role focuses on identifying vulnerabilities in large language models and strengthening their security through adversarial testing and prompt engineering.

Key responsibilities

• Design and implement red‑team strategies to uncover bias, toxicity, factual inaccuracies and other weaknesses in LLM outputs.
• Develop both automated and manual testing frameworks that simulate adversarial attacks on AI models.
• Document findings in structured reports, highlight risks and recommend mitigations.
• Collaborate with AI safety researchers to refine testing protocols based on emerging threats.
• Stay up‑to‑date with the latest AI security techniques, including prompt injection and jailbreak methods.

Required profile

• Proven experience with adversarial testing of large language models.
• Strong proficiency in Python and familiarity with AI/ML frameworks 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 documentation of vulnerabilities and recommendations.
• Awareness of ethical AI guidelines and responsible AI development practices.

Required skills

• Python
• Hugging Face
• PyTorch

What we offer

• Remote work from anywhere.
• Flexible contract schedule.
• Competitive hourly rate ranging from $40 to $65.