Frontier AI Safety Evaluator — Risk & Alignment

Obsidian; Madrid; A distancia; EUR 70.000 - 110.000; Jornada completa

Descripción de la vacante

Obsidian seeks experienced AI Safety Practitioners to evaluate the 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.

This role involves collaborating with researchers and safety teams to identify unsafe outputs, refine rubrics for RLHF/SFT, and contribute to ongoing evaluation initiatives in high-impact domains.

Formación

• 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, critical thinking, and analytical reasoning skills.
• Ability to consistently evaluate nuanced and policy-sensitive scenarios.

Responsabilidades

• 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.

Conocimientos

Analytical thinking

Critical thinking

English proficiency

Policy evaluation

Educación

Bachelor's degree or higher in a related field

Descripción del empleo

Obsidian seeks experienced AI Safety Practitioners to evaluate the 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.

This role involves collaborating with researchers and safety teams to identify unsafe outputs, refine rubrics for RLHF/SFT, and contribute to ongoing evaluation initiatives in high-impact domains.