Senior AI Safety Evaluator & Model Alignment

Mercor; Paris; Remote; EUR 90.000 - 130.000; Vollzeit

Zusammenfassung

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

Join a collaborative team to identify unsafe outputs, refine evaluation rubrics for RLHF and SFT, and contribute to safety benchmarking in real-world deployments.

Qualifikationen

• Bachelor's degree or higher in a related discipline.
• 5+ years of professional experience in AI Safety, Trust & Safety, journalism, public policy, or related field.
• Excellent written English and strong analytical reasoning.
• Ability to consistently evaluate nuanced and policy-sensitive scenarios.

Aufgaben

• 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.

Kenntnisse

Excellent written English

Analytical reasoning

Critical thinking

Policy evaluation

Attention to detail

Ausbildung

Bachelor's degree

Jobbeschreibung

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

Join a collaborative team to identify unsafe outputs, refine evaluation rubrics for RLHF and SFT, and contribute to safety benchmarking in real-world deployments.