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 role focuses on identifying vulnerabilities in large language models through adversarial testing and helping improve their safety before public release.

Key responsibilities

• Design and implement red‑teaming strategies to uncover weaknesses such as bias, toxicity, and factual inaccuracies in LLM outputs.
• Develop automated and manual testing frameworks to simulate adversarial attacks on AI models.
• Document findings in structured reports, highlighting risks and recommending mitigations.
• Collaborate with AI safety researchers to refine testing protocols based on emerging threats.
• Stay current with advancements in AI security, including prompt injection and jailbreak techniques.

Required profile

• Experience with adversarial testing of large language models, including prompt engineering and attack simulations.
• Proficiency in Python and familiarity with AI/ML frameworks such as Hugging Face or PyTorch.
• Strong knowledge of cybersecurity principles relevant to AI systems.
• Ability to analyze model outputs for bias, toxicity, and hallucinations.
• Excellent written communication for documenting vulnerabilities and recommendations.

Required skills

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

What we offer

• Remote work from anywhere
• Contract engagement with competitive hourly rate of $40‑$65
• Opportunity to influence AI safety for a global technology leader