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. /p h3Responsibilities /h3 ul liEvaluate AI-generated responses for safety, factual accuracy, policy compliance, and overall quality. /li liReview content involving misinformation, political persuasion, self-harm, violence, cyber, biosecurity, and other sensitive domains. /li liApply and refine evaluation rubrics for RLHF, SFT, and AI safety benchmarking. /li liIdentify unsafe outputs, hallucinations, reasoning failures, and policy violations. /li liProvide structured feedback to improve model alignment and safety performance. /li liCollaborate with AI researchers and safety teams on ongoing evaluation initiatives. /li /ul h3Required Qualifications /h3 ul liBachelor's degree or higher in Journalism, Communications, Psychology, Sociology, Public Policy, Law, Biology, Chemistry,



Computer Science, or a related discipline. /li li5+ years of professional experience in AI Safety, Trust Safety, journalism, public policy, scientific research, security, or a related field. /li liExcellent written English, critical thinking, and analytical reasoning skills. /li liAbility to consistently evaluate nuanced and policy-sensitive scenarios. /li /ul h3Preferred Qualifications /h3 ul liExperience with AI Safety, RLHF, SFT, Trust Safety, or AI evaluation. /li liFamiliarity with safety policies, content moderation, or evaluation rubric development. /li liExperience reviewing complex, high-risk, or ambiguous content. /li /ul h3Why Join? /h3 ul liShape the safety and behaviour of frontier AI models used by millions worldwide. /li liWork on challenging, real-world safety evaluations across nuanced and high-impact domains. /li liCollaborate with leading AI researchers, engineers, and safety teams. /li /ul /p #J-18808-Ljbffr

📌 AI Safety Specialist - Evaluation Expert (Milano)
🏢 Mercor
📍 Milano