AI Safety Evaluator: Frontier Models & Policy Alignment

Obsidian; Oslo; On-site; NOK 700,000 - 1,100,000; Full time

Job summary

Obsidian is seeking experienced AI Safety Practitioners to evaluate frontier AI models across safety, alignment, and policy-sensitive topics. You will assess AI-generated responses and help improve model behavior through structured evaluations.

You will review content involving misinformation, political persuasion, self-harm, violence, and other high-risk domains, identifying unsafe outputs and policy violations.

Qualifications

• Bachelor's degree or higher in Journalism, Communications, Psychology, Sociology, Public Policy, Law, Biology, Chemistry, Computer Science, or related field.
• 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.
• Ability to evaluate nuanced and policy-sensitive scenarios.

Responsibilities

• Evaluate AI-generated responses for safety, accuracy, policy compliance, and quality.
• Review content involving misinformation, political persuasion, self-harm, violence, and other high-risk domains.
• Apply and refine evaluation rubrics for RLHF, SFT, and AI safety benchmarking.
• Identify unsafe outputs, hallucinations, and policy violations, with actionable feedback.

Skills

Excellent written English

Critical thinking

Analytical reasoning

Nuanced policy evaluation

Education

Bachelor's degree or higher

Job description

Obsidian is seeking experienced AI Safety Practitioners to evaluate frontier AI models across safety, alignment, and policy-sensitive topics. You will assess AI-generated responses and help improve model behavior through structured evaluations.

You will review content involving misinformation, political persuasion, self-harm, violence, and other high-risk domains, identifying unsafe outputs and policy violations.