2 months ago
Responsibilities
- Analyze latency, memory, power, and numerical correctness of machine learning models running on Apple devices.
- Optimize ML inference performance across CPU, GPU, and Apple Neural Engine hardware.
- Implement models in the ML software stack and perform model import and conversion.
- Write Python, C++, and shell scripts and build utilities and debugging tools for performance and power analysis.
- Generate, extract, analyze, and report performance and power metrics for Apple hardware.
- Collaborate with research, software engineering, hardware engineering, and product teams.
Requirements
- Experience with ML inference, quantization, and performance-versus-accuracy tradeoffs.
- Familiarity with ML architectures such as large language models, diffusion models, and convolutional neural networks.
- Knowledge of operating systems, embedded systems, and CPU, GPU, SoC, memory, and computer architectures.
- High proficiency in Python, C++, and shell scripting.
- Familiarity with Linux or macOS.
- Strong verbal and written communication skills, including the ability to summarize, present, and lead group discussions.
- Preferred: Master's or PhD in computer science or a related discipline.
- Preferred: Experience with Core ML, MPS Graph, Metal Performance Shaders, MLX, PyTorch, TensorFlow, JAX, TFLite, ONNX, ExecuTorch, MLIR, LLVM, or TVM.
- Preferred: Experience implementing high-performance compute kernels for CPUs, GPUs, or AI accelerators.
- Preferred: Experience with Xcode, Swift, Objective-C, or on-device ML stacks.
Categories
About Apple
Apple designs and sells consumer electronics, software, and services for consumers and professionals worldwide, including iPhone, Mac, iPad, Apple Watch, and AirPods, plus platforms like iOS/macOS and services such as the App Store, iCloud, Music, and TV+. Its business combines device sales with services and subscriptions and in-house silicon design. Founded in 1976, Apple is headquartered in Cupertino, California, and trades on NASDAQ as AAPL.