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 maximum performance and energy efficiency.
• Implement ML models into the software stack to achieve full machine performance on Apple Silicon.
• Develop scripts and tools to extract, analyze, and report performance and power metrics.
• Debug performance and power consumption issues across CPU, GPU, and Apple Neural Engine.
• Perform deep analysis of ML model architectures to identify performance and accuracy tradeoffs.
• Generate and present ML performance data 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/SoC/Memory HW 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.
• Masters or PhDs in Computer Science or relevant disciplines (preferred).
• Experience with Apple frameworks (CoreML, MPS, Metal, MLX) or ML authoring frameworks (PyTorch, TensorFlow, JAX) (preferred).