Evaluation Science Lead
Core
Define and validate multilingual Globalization AI solutions across 50+ languages for Apple Services using statistically grounded evaluation frameworks.
Role type
Senior IC evaluation science lead
Builds
Evaluation frameworks, statistical methodologies, and scalable validation workflows for AI models
Domain
AI/ML, Globalization, Multilingual NLP
Deliverable
production ML models
Required skills
statistical methodology, experimental design, human annotation protocols, LLM-as-judge systems, data analysis, R, Python, SQL
Preferred skills
generative AI evaluation, causal inference, applied linguistics, benchmark design
Technologies
R, Python, SQL, LLM-as-judge, autograders
Responsibilities
Design long-term evaluation science strategy and roadmap; Architect scalable workflows blending human annotation with automated systems; Translate evaluation data into actionable recommendations for engineering; Build continuous performance monitoring and drift-detection systems
Seniority
Senior, hands-on IC