Frontier AI Safety Red Teamer

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

Job summary

Mercor in Ireland 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.

Responsibilities include stress-testing frontier AI models, identifying jailbreaks, unsafe behaviours, and policy failures; documenting vulnerabilities; and collaborating with researchers to improve alignment, robustness, and safety.

Qualifications

• Bachelor's degree or higher in a related discipline.
• 5+ years of AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or 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

Adversarial prompts

Prompt design

Analytical reasoning

Written communication

Education

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

Job description

Mercor in Ireland 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.

Responsibilities include stress-testing frontier AI models, identifying jailbreaks, unsafe behaviours, and policy failures; documenting vulnerabilities; and collaborating with researchers to improve alignment, robustness, and safety.