Cybersecurity Consultant – LLM Red‑Teamer (Remote)

About the role

We are seeking a Cybersecurity Consultant to join a leading technology client on a contract basis. The focus is on red‑teaming large language models (LLMs) to uncover vulnerabilities, bias, toxicity, and factual inaccuracies through adversarial testing.

Key responsibilities

• Design and execute red‑teaming strategies that probe LLM behavior under edge‑case and malicious inputs.
• Develop automated and manual testing frameworks to simulate prompt injection, jailbreaks, and other attacks.
• Document findings in structured reports, highlighting risks and recommending mitigations.
• Collaborate with AI safety researchers to refine testing protocols and stay ahead of emerging threats.
• Continuously monitor advancements in AI security, including new adversarial techniques.

Required profile

• Proven experience with adversarial testing of LLMs and prompt engineering.
• Strong understanding of cybersecurity principles as they apply to AI systems.
• Excellent written communication skills for clear documentation of vulnerabilities.
• Ability to work independently in a fully remote environment.

Required skills

• Python programming.
• Familiarity with AI/ML frameworks such as Hugging Face and PyTorch.
• Prompt engineering and attack simulation techniques.
• Adversarial testing of large language models.

What we offer

• Fully remote work from anywhere.
• Contract engagement with competitive hourly rates ($40‑$65/hr).
• Opportunity to influence the safety of cutting‑edge AI products.