On-device ML Infrastructure Engineer (ML Insights and Forecasting)

We are building the first end-to-end developer experience for ML development that, by taking advantage of Apple’s vertical integration, allows developers to iterate on model authoring, optimization, transformation, execution, debugging, profiling and analysis. This role provides a great opportunity to bring the latest ML architectures and trends to our on device inference stack. Work includes prototyping to get new ideas working, building infrastructure to enable regular coverage, and collaborating with inference stack teams to make any changes needed to enable new architectures/features as well as deliver full machine performance. The role contributes to building the first end-to-end developer experience for ML development that, by taking advantage of Apple’s vertical integration, allows developers to iterate on model authoring, optimization, transformation, execution, debugging, profiling and analysis. The role further offers a learning platform to dig into the latest research about on-device machine learning, an exciting ML frontier! Possible example areas include model visualization, efficient inference algorithms, model compression, and/or ML compilers/run-time. Key Responsibilities: - Explore the latest ML model architectures and prototype getting these running on device. - Build infrastructure to enable at scale testing of new ML features. - Analyze achieved performance vs roofline models on Apple’s hardware. - Analyze telemetry data to understand how users are using ML on device. - Identify gaps in today’s ML inference stack and work with XF teams to prioritize and address these. - Collaborate extensively with ML and hardware teams across Apple.