AI Safety Evaluator & Model Alignment Specialist

Mercor; København; Remote; DKK 700,000 - 1,000,000; Full time

Job summary

Mercor seeks experienced AI Safety Practitioners to evaluate the safety, quality, and alignment of frontier AI models on sensitive topics. You will assess AI-generated responses, apply safety policies, and provide structured feedback.

This role involves collaborating with researchers and safety teams to refine rubrics for RLHF, SFT, and AI safety benchmarking, and to identify unsafe outputs and policy violations.

Qualifications

• Bachelor's degree or higher in a related discipline.
• 5+ years of professional experience in AI Safety, Trust & Safety, journalism, public policy, scientific research, security, or related field.
• Excellent written English, critical thinking, and analytical reasoning skills.

Responsibilities

• Evaluate AI-generated responses for safety, factual accuracy, policy compliance, and overall quality.
• Review content involving misinformation, political persuasion, self-harm, violence, cyber, biosecurity, and other sensitive domains.
• Apply and refine evaluation rubrics for RLHF, SFT, and AI safety benchmarking.
• Identify unsafe outputs, hallucinations, reasoning failures, and policy violations.
• Provide structured feedback to improve model alignment and safety performance.
• Collaborate with AI researchers and safety teams on ongoing evaluation initiatives.

Skills

Excellent written English

Critical thinking

Analytical reasoning

Education

Bachelor's degree or higher in Journalism/Communications/Psychology/Sociology/Public Policy/Law/Biology/Chemistry/CS or related

Job description

Mercor seeks experienced AI Safety Practitioners to evaluate the safety, quality, and alignment of frontier AI models on sensitive topics. You will assess AI-generated responses, apply safety policies, and provide structured feedback.

This role involves collaborating with researchers and safety teams to refine rubrics for RLHF, SFT, and AI safety benchmarking, and to identify unsafe outputs and policy violations.