ML - Data Scientist
Core
Design and maintain evaluation systems, human-annotation programs, and automated metrics to measure the quality of generative image and video features for Apple devices.
Role type
Senior IC machine-learning evaluation scientist (generative AI)
Builds
Evaluation systems, annotation tools, automated metrics, and quality signals guiding model release decisions
Domain
Consumer technology / Generative AI / Quality Assurance
Deliverable
production ML models
Required skills
Statistical analysis, experimental design, Python, SQL, human evaluation program management, automated metric development, LLM-as-judge system calibration, confidence interval calculation, significance testing
Preferred skills
3D Gaussian splats evaluation, diffusion model assessment, perceptual quality metrics, web-based labeling tool development, parallel work-stream management
Technologies
Python, SQL, LLMs, VLMs, annotation tools
Responsibilities
Design and maintain golden sets and evaluation sets; write and iterate annotation guidelines and label schemas; develop automated metrics and LLM-as-judge systems; report model comparisons with statistical analysis; define quality standards with cross-functional partners
