Frontier AI Safety Red Teamer

Mercor; Stockholms kommun; Remote; SEK 700,000 - 1,000,000; Full time

Job summary

Mercor in Sweden is seeking experienced AI Safety Red Teamers to stress-test frontier AI models. You will design adversarial prompts, uncover jailbreaks, and assess safety across high-risk domains.

You will document vulnerabilities, contribute to safety benchmarking, and collaborate with researchers to improve model alignment and robustness. The role requires 5+ years in AI safety or related fields, plus strong analytical and writing skills.

Qualifications

• Bachelor's degree or higher in Computer Science, Cybersecurity, or related field.
• 5+ years of professional experience in AI Safety, red teaming, or safety research.
• 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

Prompt design

Adversarial testing

AI Safety

Model alignment

Safety reporting

Education

Bachelor's degree or higher in related field

Tools

RLHF

SFT

Job description

Mercor in Sweden is seeking experienced AI Safety Red Teamers to stress-test frontier AI models. You will design adversarial prompts, uncover jailbreaks, and assess safety across high-risk domains.

You will document vulnerabilities, contribute to safety benchmarking, and collaborate with researchers to improve model alignment and robustness. The role requires 5+ years in AI safety or related fields, plus strong analytical and writing skills.