Remote AI Safety Red Teamer for Frontier Models

Mercor; Helsinki; Remote; EUR 90,000 - 120,000; Full time

Job summary

Mercor in Helsinki seeks experienced AI Safety Red Teamers to stress-test frontier AI systems. You will design challenging prompts, uncover model weaknesses, and assess behavior across high-risk topics.

Responsibilities include identifying jailbreaks, unsafe behaviours, hallucinations, and policy failures, and documenting vulnerabilities for safety benchmarking. You will collaborate with AI researchers to improve alignment and robustness.

Qualifications

• Bachelor's degree or higher in a related field.
• 5+ years of professional AI safety or red teaming experience.
• Strong analytical reasoning and prompt design 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.

Education

Bachelor's degree or higher in CS, cybersecurity, journalism, communications, psychology, biology, chemistry, public policy, or related discipline

5+ years of AI safety/red teaming experience

Prompt design and analytical reasoning

Experience designing adversarial prompts

Written communication skills

Job description

Mercor in Helsinki seeks experienced AI Safety Red Teamers to stress-test frontier AI systems. You will design challenging prompts, uncover model weaknesses, and assess behavior across high-risk topics.

Responsibilities include identifying jailbreaks, unsafe behaviours, hallucinations, and policy failures, and documenting vulnerabilities for safety benchmarking. You will collaborate with AI researchers to improve alignment and robustness.