Machine Learning Evaluation Engineer at Apple, focused on ML model quality, LLM evaluation, and AI features for Creativity Apps.

This engineer defines evaluation strategies and metrics for models, products, and use cases. The role builds datasets and scalable infrastructure while driving quality from model development through shipping features. Collaboration spans machine learning engineering, infrastructure, product, and design teams to reflect creators’ experiences.

Key Responsibilities

Define metrics for ML models, LLMs, and AI features

Create representative datasets and improve dataset quality iteratively

Build scalable infrastructure with reproducible runs and tracked baselines

Apply automated judging, test generation, and analysis workflows





Report ship risks and recommendations to diverse audiences

Requirements

Five-plus years in machine learning or software engineering

Experience evaluating ML models, LLMs, and AI products

Understanding of training, deployment, evaluation, and monitoring

Proficiency in Python, Swift, or comparable languages

Bachelor’s degree or equivalent experience in a related field

Apply ML fundamentals, LLM knowledge, dataset curation, and quality reporting to Apple’s creativity applications.

📌 Machine Learning Evaluation Engineer Apple (Winnipeg)
🏢 Apple
📍 Winnipeg