Evaluation Science Lead – Globalization AI (Onsite + Travel)

Apple Inc.; Austin (TX); Vor Ort; USD 170.000 - 210.000; Vollzeit

Zusammenfassung

Apple Inc. in Austin, Texas seeks an Evaluation Science Lead to define how multilingual Globalization AI solutions are measured and validated across Apple Services, including Apple Music and App Store.

This is a rare opportunity to build evaluation science at the intersection of language, culture, and AI. You will design statistically grounded evaluation frameworks combining human judgment with scalable automation, partnering with Engineering, AI Strategy, and Production to turn evaluation into

Qualifikationen

• 5+ years of experience in evaluation science, data science, or ML systems development with end-to-end ownership of evaluation systems.
• Experience applying statistical methodologies (sampling, significance testing, confidence intervals) and measurement validity principles.
• Hands-on experience measuring annotator agreement and improving annotation protocols.

Aufgaben

• Define the long-term evaluation science strategy and roadmap for Globalization AI solutions across 50+ languages.
• Design robust statistical methodologies and scalable evaluation workflows with human annotation and automated scoring.
• Translate evaluation data into actionable recommendations and go/no-go evidence for Engineering and leadership.
• Build continuous performance monitoring and drift-detection to distinguish real issues from noise.
• Serve as the resident authority on multilingual AI evaluation and promote best practices.

Kenntnisse

Evaluation science

Data science

ML systems development

Ausbildung

Master’s or PhD or equivalent

Tools

R

Python

SQL

Jobbeschreibung

Apple Inc. in Austin, Texas seeks an Evaluation Science Lead to define how multilingual Globalization AI solutions are measured and validated across Apple Services, including Apple Music and App Store.

This is a rare opportunity to build evaluation science at the intersection of language, culture, and AI. You will design statistically grounded evaluation frameworks combining human judgment with scalable automation, partnering with Engineering, AI Strategy, and Production to turn evaluation into