Senior Frontier AI Safety Red Teamer

Obsidian; Amsterdam; Remote; EUR 90,000 - 130,000; Full time

Job summary

Obsidian in Amsterdam seeks experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across high-risk topics.

Join a team of researchers to push forward model alignment, robustness, and safety. You will document vulnerabilities and contribute to safety benchmarking while collaborating across disciplines.

Qualifications

• Bachelor's degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or a related discipline.
• 5+ years of professional experience in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or a related field.
• Strong analytical reasoning, prompt design, and written communication skills.

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

Analytical thinking

Prompt design

Written communication

Education

Bachelor's degree or higher in Computer Science or related disciplines

Job description

Obsidian in Amsterdam seeks experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across high-risk topics.

Join a team of researchers to push forward model alignment, robustness, and safety. You will document vulnerabilities and contribute to safety benchmarking while collaborating across disciplines.