On-device ML Performance Engineer, Graphics, Games and Machine Learning

What you'll do

• Analyze latency, memory, power, and numerical correctness of machine learning models on Apple SoCs.
• Optimize model conversion, compilation, and inference to improve performance and energy efficiency.
• Develop tools and scripts to extract and analyze performance and power metrics for hardware.
• Perform deep analysis of the ML stack from software layers down to low-level drivers.
• Implement optimization techniques such as quantization and sparsity for various ML architectures.
• Debug issues involving CPU, GPU, Apple Neural Engine, system memory, and power.
• Report and present performance data to internal and external stakeholders.

What we're looking for

• Experience with ML inference, quantization, performance, and accuracy.
• Familiarity with popular ML architectures including LLMs, Diffusion models, and CNNs.
• Knowledge of Operating Systems, embedded systems, and CPU/GPU hardware architectures.
• Proficiency in Python, C++, and shell scripting.
• Familiarity with Linux or macOS operating systems.
• Strong verbal and written communication skills for presenting to large groups.
• Master's or PhD in Computer Science or a related field is preferred.
• Experience with frameworks like CoreML, Metal Performance Shaders, PyTorch, or compiler stacks like MLIR/LLVM.