AIML - Machine Learning Engineer, Model Evaluations

This role focuses on evaluating and mitigating safety risks in generative AI features within Apple Intelligence. The responsibilities include developing metrics for safety and fairness evaluations, designing datasets, collaborating with cross-functional teams, translating regional safety requirements into evaluation criteria, building expertise in machine translation and data synthesis, and developing ML-based enhancements to improve product quality. The role involves working with highly sensitive and potentially offensive content. The candidate will work at the intersection of applied data science, empirical analysis, cultural and linguistic expertise, and stakeholder communication.