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

What you'll do

• Analyze latency, memory, power, and numerical correctness of ML models running on Apple SoCs.
• Optimize model conversion, compilation, and on-device inference for performance and energy efficiency.
• Develop tools and scripts to extract, analyze, and report ML performance and power metrics.
• Perform deep analysis of ML inference across the software stack, low-level drivers, and hardware.
• Debug hardware performance involving CPU, GPU, Apple Neural Engine, system memory, and power.
• Evaluate performance and accuracy tradeoffs using techniques like quantization and sparsity.
• Present ML performance data and analysis to internal and external stakeholders.

What we're looking for

• Experience with ML inference, quantization, performance, and accuracy.
• Familiarity and experience with popular ML architectures like LLMs, Diffusion models, and CNNs.
• Familiarity with Operating Systems, embedded systems, and CPU/GPU hardware architectures.
• Highly proficient in Python, C++, and shell scripting.
• Familiarity with Linux or macOS.
• Exceptional clarity in verbal and written communication, including the ability to lead discussions in large groups.
• Masters or PhDs in Computer Science or relevant disciplines (preferred).
• Experience with Apple frameworks (CoreML, MPS Graph, Metal, MLX, Xcode, Swift, Objective-C) or ML authoring frameworks (PyTorch, TensorFlow, JAX) (preferred).