LLM Red‑Teamer – Cybersecurity Consultant (Remote)

About the role

We are seeking an experienced Cybersecurity Consultant to join a leading technology firm on a contract basis. The focus is on red‑team testing of large language models (LLMs) to uncover vulnerabilities, bias, toxicity, and factual inaccuracies. This fully remote position allows you to work from anywhere while contributing to safer AI deployments.

Key responsibilities

• Design and execute red‑team strategies that probe LLM behavior under edge‑case and malicious inputs.
• Develop both automated and manual testing frameworks to simulate adversarial attacks.
• Document findings in structured reports, highlighting risks and recommending 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 in adversarial testing of LLMs or similar AI systems.
• Strong understanding of cybersecurity principles as they apply to AI.
• Excellent written communication skills for clear documentation of vulnerabilities.
• Familiarity with ethical AI guidelines and responsible development practices.

Required skills

• Python programming.
• Experience with AI/ML frameworks such as Hugging Face and PyTorch.
• Prompt engineering and attack simulation techniques.

What we offer

• Contract engagement with a global leader in technology, information, and internet services.
• Competitive hourly rate of $40‑$65.
• Opportunity to influence AI model deployment decisions before public release.