On-Device ML Infra Engineer: Graph & Runtime

Apple, Inc.; Cupertino (CA); On-site; USD 185,000 - 325,000; Full time

Benefits offered by this job

Medical and dental benefits

Retirement benefits

Employee stock programs

Relocation assistance

Job summary

Apple is seeking an On-Device ML Infrastructure Engineer focused on graph compilers and runtimes for the Core ML Runtime. You will help build the world’s most advanced ML graph compilation and runtime system to optimize and deliver ML models efficiently on Apple products and services.

The role involves architecting the on-device graph compiler, runtime, and kernels, developing production-grade system software, and optimizing for performance, energy, and thermals.

Qualifications

• Masters degree or equivalent experience in Computer Science, Engineering, or related field.
• Highly proficient in C++ or Swift; familiarity with Python.
• Experience with any compiler stack (MLIR/LLVM/TVM/...).
• Familiarity with Operating Systems, embedded programming, parallel programming.
• Strong ML fundamentals, including Transformers.
• Good communication skills for cross-functional audiences.

Responsibilities

• Architect and maintain the on-device graph compiler, runtime, and kernels for delivering ML operators.
• Develop production-critical system software for implementing ML models on Apple Silicon.
• Proactively identify and resolve functionality gaps.
• Optimize model execution for performance, energy efficiency, and thermal management.

Skills

C++

Swift

Python

Compiler stack (MLIR/LLVM/TVM)

Operating Systems

Embedded Programming

Parallel Programming

ML Fundamentals

Transformers

Communication Skills

On-device ML Stack

ML Frameworks

GPU Programming

Education

Masters or equivalent experience in Computer Sciences, Engineering, or related subject area

Job description

Apple is seeking an On-Device ML Infrastructure Engineer focused on graph compilers and runtimes for the Core ML Runtime. You will help build the world’s most advanced ML graph compilation and runtime system to optimize and deliver ML models efficiently on Apple products and services.

The role involves architecting the on-device graph compiler, runtime, and kernels, developing production-grade system software, and optimizing for performance, energy, and thermals.