Frontier AI Safety Red Team Expert

Obsidian; New York (NY); Remote; USD 140,000 - 210,000; Full time

Job summary

Obsidian is seeking experienced AI Safety Red Teamers to stress-test frontier AI models through adversarial testing and prompt design. You will identify jailbreaks, unsafe behaviours, and policy failures while evaluating model behavior across sensitive domains.

Collaborating with AI researchers, you will contribute to safety benchmarking, vulnerability documentation, and research to improve alignment and robustness of frontier AI systems.

Qualifications

• Strong analytical reasoning, prompt design, and written communication skills.
• Experience designing adversarial prompts or evaluating frontier AI systems.

Responsibilities

• Design adversarial prompts to stress-test frontier AI models.
• Identify jailbreaks, unsafe behaviours, hallucinations, and policy failures.
• Evaluate model robustness across misinformation, cyber, biosecurity, fraud, political content, and other sensitive domains.
• Document vulnerabilities and contribute to safety benchmarking and red-teaming reports.
• Collaborate with AI researchers to improve model alignment, robustness, and safety.

Skills

Prompt design

Analytical reasoning

Written communication

Adversarial testing

Education

Bachelor’s degree or higher in a related field

Job description

Obsidian is seeking experienced AI Safety Red Teamers to stress-test frontier AI models through adversarial testing and prompt design. You will identify jailbreaks, unsafe behaviours, and policy failures while evaluating model behavior across sensitive domains.

Collaborating with AI researchers, you will contribute to safety benchmarking, vulnerability documentation, and research to improve alignment and robustness of frontier AI systems.