On-Device ML Performance Engineer for Graphics & Inference

Apple Inc.; Seattle (WA); On-site; USD 142,000 - 263,000; Full time

Benefits offered by this job

Medical & dental coverage

Stock programs

Tuition reimbursement

Relocation assistance

Job summary

Apple Inc. is seeking an On-device ML Performance Engineer to analyze and optimize ML model performance on latest iPhones and Macs. You will work across CPU, GPU, Apple Neural Engine, and memory to ensure the stack achieves peak efficiency on Apple Silicon.

The role involves scripting, coding, and building tools to extract and report performance and power metrics, leveraging ML architectures and HW drivers. Strong Python/C++ skills and OS familiarity are essential.

Qualifications

• Experience with ML inference, quantization, performance and accuracy.
• Familiarity with popular ML architectures (LLMs, diffusion models, CNNs).
• Interest in latest ML model design and on-device inference.
• Familiarity with OS, embedded systems, CPU/GPU HW architectures.
• Proficient in Python/C++ and shell scripting.
• Experience with Linux or macOS.
• Excellent verbal and written communication.

Responsibilities

• Drive on-device performance analysis of Apple SoCs and ML software stack.
• Optimize model conversion, compilation and on-device inference for SoCs.
• Develop tools/scripts to generate and analyze ML performance data.
• Collaborate across teams to deliver best in class on-device ML hardware and software stack.
• Present ML performance data to internal and external teams.

Skills

ML inference

Quantization

Performance optimization

Model architectures

Python

C++

Shell scripting

Linux/macOS

Strong communication

Education

Masters or PhDs in Computer Science or relevant disciplines

Tools

CoreML

MPS Graph

Metal Performance Shaders

MLX frameworks

Job description

Apple Inc. is seeking an On-device ML Performance Engineer to analyze and optimize ML model performance on latest iPhones and Macs. You will work across CPU, GPU, Apple Neural Engine, and memory to ensure the stack achieves peak efficiency on Apple Silicon.

The role involves scripting, coding, and building tools to extract and report performance and power metrics, leveraging ML architectures and HW drivers. Strong Python/C++ skills and OS familiarity are essential.