AI Safety Specialist – Remote (Contract)

About the role

We are looking for an AI Safety Specialist to join our remote team on a contract basis. You will work closely with AI researchers to stress‑test cutting‑edge models and help ensure they behave safely across a range of high‑risk domains.

Key responsibilities

• Design adversarial prompts that probe frontier AI models for weaknesses.
• Identify jailbreaks, unsafe behaviours, hallucinations, and policy failures.
• Evaluate model robustness against misinformation, cyber threats, biosecurity risks, fraud, political content and other sensitive areas.
• Document discovered vulnerabilities and contribute to safety benchmarking and red‑team reports.
• Collaborate with researchers to improve model alignment, robustness and overall safety.

Required profile

• Bachelor’s degree or higher in a relevant discipline (e.g., Computer Science, Cybersecurity, Life Sciences, Public Policy).
• 5+ years of professional experience in AI safety, red‑team testing, trust & safety, cybersecurity, investigative journalism or related fields.
• Strong analytical reasoning, prompt‑design expertise and excellent written communication.
• Proven experience creating adversarial prompts or evaluating frontier AI systems.

Required skills

• Prompt engineering and adversarial testing.
• AI Red Teaming, Reinforcement Learning from Human Feedback (RLHF) and Supervised Fine‑Tuning (SFT).
• Familiarity with jailbreak testing and AI alignment concepts.
• Domain knowledge in cyber, biosecurity, political content, misinformation or scientific safety.

What we offer

• Competitive hourly rate of $70–$84.
• Fully remote work with flexible hours.
• Opportunity to influence safety practices for leading AI research labs.