Frontier AI Safety Evaluator & Alignment Expert

Obsidian; Zürich; Vor Ort; CHF 120.000 - 170.000; Vollzeit

Zusammenfassung

Obsidian, Zürich, seeks experienced AI Safety Practitioners to evaluate the safety, quality, and alignment of frontier AI models on grey-area topics.

You will assess AI-generated responses, apply safety policies, and provide structured feedback to help improve model behavior, working closely with AI researchers and safety teams.

A Bachelor's degree plus 5+ years in AI safety or related fields are required, with strong English writing and analytical skills to navigate policy-sensitive scenarios.

Qualifikationen

• Bachelor's degree or higher in a related discipline (see qualifications).
• Minimum 5+ years in AI Safety, Trust & Safety, journalism, public policy, or related field.
• Excellent written English and strong analytical skills.
• Ability to evaluate nuanced, policy-sensitive scenarios consistently.

Aufgaben

• Evaluate AI-generated responses for safety, factual accuracy, policy compliance, and quality.
• Review content on 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 evaluation initiatives.

Kenntnisse

Written English

Critical thinking

Analytical reasoning

Nuanced policy evaluation

Ausbildung

Bachelor's degree in a related field

Jobbeschreibung

Obsidian, Zürich, seeks experienced AI Safety Practitioners to evaluate the safety, quality, and alignment of frontier AI models on grey-area topics.

You will assess AI-generated responses, apply safety policies, and provide structured feedback to help improve model behavior, working closely with AI researchers and safety teams.

A Bachelor's degree plus 5+ years in AI safety or related fields are required, with strong English writing and analytical skills to navigate policy-sensitive scenarios.