Apple - Cupertino, CA
posted 3 months ago
The Machine Learning and Platforms Technology (MLPT) team is part of Apple's AIML Organization, focusing on building the inference stack that runs all machine learning (ML) networks on Apple Silicon. This team is responsible for writing the converter and compiler that translates source network definitions into formats that execution units in hardware can interpret. Additionally, the team develops tools for network optimizations and writes the runtime that schedules and manages execution on hardware. They also provide guidance for hardware/software co-design of current and future workloads alongside hardware accelerators. The MLPT team collaborates cross-functionally with various partner teams within Apple, including CPU, GPU, Neural Engine, speech understanding, Camera, Photos, and VisionPro, as well as with external app developers. Core ML is an example of an external-facing product developed by this team. In this role, you will delve into the latest research on efficient on-device inference, prototyping new approaches to enhance inference on critical models without compromising accuracy. You will conduct deep dive analyses of both the software stack and hardware, devising innovative methods for improvement. The role also involves evaluating ML inference performance across a spectrum of devices, from small wearables to the largest Apple Silicon Macs.