Multilingual Globalization AI Evaluation Lead

Apple, Inc.; Austin (TX); On-site; USD 180,000 - 230,000; Full time

Job summary

Apple, Inc. in Austin, TX is seeking an Evaluation Science Lead to define how multilingual Globalization AI solutions are measured and validated across Apple Services—including Music, App Store, TV+, and Podcasts.

This role blends language, culture, and AI to ensure evaluation becomes a strategic capability. You will design statistically grounded evaluation frameworks, marry human judgment with automation, and collaborate with Engineering, AI Strategy, and Production to operationalize evaluation

Qualifications

• 5+ years in evaluation science or ML systems at scale
• Experience applying statistical methods: sampling, significance testing, confidence intervals
• Proficiency with R, Python, SQL for analysis and reproducibility
• Strong written and verbal communication for technical and non-technical audiences

Responsibilities

• Define the long-term evaluation strategy for Globalization AI across 50+ languages
• Design robust statistical methodologies and thresholds for model evaluation
• Architect scalable evaluation workflows blending human annotation with automation
• Expand evaluation criteria beyond linguistic quality to include behavioral signals
• Translate evaluation data into clear, actionable recommendations for Engineering and leadership
• Build monitoring and drift-detection systems to distinguish real regressions from noise
• Establish feedback loops with Quality Operations and Engineering to refine rubrics
• Serve as the resident authority on multilingual AI evaluation across Apple Services

Skills

Evaluation science

Statistics

Python

R

SQL

Communication

Education

Master’s or PhD in Statistics/Quantitative field

Tools

Python

R

SQL

Job description

Apple, Inc. in Austin, TX is seeking an Evaluation Science Lead to define how multilingual Globalization AI solutions are measured and validated across Apple Services—including Music, App Store, TV+, and Podcasts.

This role blends language, culture, and AI to ensure evaluation becomes a strategic capability. You will design statistically grounded evaluation frameworks, marry human judgment with automation, and collaborate with Engineering, AI Strategy, and Production to operationalize evaluation