ppWe are seeking experienced bAI Safety Practitioners /b to evaluate the safety, quality, and alignment of frontier AI models across complex, policy-sensitive, and ambiguous ("grey-area") topics.
You will assess AI-generated responses, apply safety policies, and help improve model behavior through structured evaluations and feedback.
/ph3Responsibilities /h3ullipEvaluate AI-generated responses for safety, factual accuracy, policy compliance, and overall quality.
/p /lilipReview content involving misinformation, political persuasion, self-harm, violence, cyber, biosecurity, and other sensitive domains.
/p /lilipApply and refine evaluation rubrics for RLHF, SFT, and AI safety benchmarking.
/p /lilipIdentify unsafe outputs, hallucinations, reasoning failures, and policy violations.
/p /lilipProvide structured feedback to improve model alignment and safety performance.
/p /lilipCollaborate with AI researchers and safety teams on ongoing evaluation initiatives.
/p /li /ulh3Required Qualifications /h3ullipBachelor's degree or higher in Journalism, Communications, Psychology, Sociology, Public Policy, Law, Biology, Chemistry,



Computer Science, or a related discipline.
/p /lilip5+ years of professional experience in AI Safety, Trust Safety, journalism, public policy, scientific research, security, or a related field.
/p /lilipExcellent written English, critical thinking, and analytical reasoning skills.
/p /lilipAbility to consistently evaluate nuanced and policy-sensitive scenarios.
/p /li /ulh3Preferred Qualifications /h3ullipExperience with AI Safety, RLHF, SFT, Trust Safety, or AI evaluation.
/p /lilipFamiliarity with safety policies, content moderation, or evaluation rubric development.
/p /lilipExperience reviewing complex, high-risk, or ambiguous content.
/p /li /ulh3Why Join?
/h3ullipShape the safety and behaviour of frontier AI models used by millions worldwide.
/p /lilipWork on challenging, real-world safety evaluations across nuanced and high-impact domains.
/p /lilipCollaborate with leading AI researchers, engineers, and safety teams.
/p /li /ul /p #J-*****-Ljbffr

📌 Ai Safety Practitioner - Expert Evaluator (Lazio)
🏢 Obsidian
📍 Lazio