Machine Learning Engineer - Intelligent Quality Systems

Job description

Our team of applied ML and software engineers builds intelligent systems that help Apple's OS software ship faster and with higher quality. We apply state-of-the-art ML, LLMs, computer vision, retrieval systems, and large-scale data analysis throughout the software lifecycle. If you're excited by using ML to solve real, large-scale problems in software quality, we have challenging and meaningful work to do together. Description The Intelligent Quality Systems team designs and builds ML-powered systems that transform how Apple approaches software quality at scale. We work across the testing lifecycle: intelligently selecting which tests are most relevant to a code change, automatically triaging test failures to their root cause, validating UI and audio experiences with vision models, surfacing test coverage gaps from change descriptions and defect history, and building the data platforms that tie it all together. In this role, you'll bring ML ideas to life on real-world, large-scale software systems. You'll prototype and evaluate techniques for problems like change-impact prediction, LLM-powered failure analysis, multimodal UI regression detection, and automated test recommendation. You'll design data collection and evaluation strategies, work with large-scale test result and code change data, and build systems robust enough to operate reliably across one of the world's largest software engineering organizations. You will be a crucial bridge between research ideas and production reality, identifying gaps in data quality, modeling assumptions, and system design before they become issues at scale. You'll succeed here if you enjoy turning ideas into working ML systems, care deeply about measurement and rigorous evaluation, and find it rewarding to see your work directly improve the productivity and quality of software shipped to hundreds of millions of people. Responsibilities: Implement and refine ML solutions across the testing lifecycle, test selection, failure triage, visual validation, and test coverage analysis Rapidly prototype multiple algorithmic approaches to identify the most promising directions Design and implement data collection, labeling, and evaluation strategies for training and measuring ML systems Work with large-scale test result and code change data to surface patterns and inform modeling decisions Proactively identify research-to-producti…