Frontier AI Safety Red Teamer

Mercor; Helsinki; Remote; EUR 90,000 - 140,000; Full time

Job summary

Mercor in Helsinki 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 behavior on complex, high-risk topics.

Responsibilities include documenting vulnerabilities, contributing to safety benchmarking, and collaborating with AI researchers to improve alignment, robustness, and safety. This role requires strong analytical and written communication skills.

Qualifications

• Bachelor's degree or higher in CS, Cybersecurity, Journalism, Communications, Psychology, or related field.
• 5+ years of professional experience in AI Safety, red teaming, or trust & safety.
• 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, and policy failures.
• Evaluate model robustness across sensitive domains such as cyber and biosecurity.
• Document vulnerabilities and contribute to safety benchmarking reports.
• Collaborate with researchers to improve alignment, robustness and safety.

Skills

Prompt design

Analytical reasoning

Written communication

Red Teaming

Adversarial testing

Education

Bachelor's degree or higher (CS/CS-related)

Job description

Mercor in Helsinki 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 behavior on complex, high-risk topics.

Responsibilities include documenting vulnerabilities, contributing to safety benchmarking, and collaborating with AI researchers to improve alignment, robustness, and safety. This role requires strong analytical and written communication skills.