Machine Learning Engineer - AI & ML Evaluation Frameworks

Apple is seeking an exceptional Machine Learning Engineer to join their Health Sensing Machine Learning Interpretability & Analytics (MLIA) team. The role involves architecting and building large-scale evaluation frameworks for machine learning systems, leading deep-dive evaluations, and translating findings into actionable insights to improve the safety and reliability of Apple's health features.

Responsibilities:

• Design robust methodologies and scalable frameworks to assess the performance, reliability, and safety of both traditional ML and foundation models (e.g., LLMs, diffusion models)
• Drive failure analysis along with building instrumentation to detect clinical hallucinations, reasoning flaws, and edge cases
• Expand LLM/diffusion-based data generation pipelines that enable model training and evaluation without exposing real user data
• Build data adaptors and visualizers to fuse asynchronous time-series signals (wearables, camera, behavioral metadata)
• Develop generalizable tools and metrics to discover biases and measure demographic equity across diverse populations
• Translate evaluation results into actionable engineering insights for GenAI researchers, algorithm leads, and clinical experts