On-Device ML Graph Compiler Engineer

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

Benefits offered by this job

Medical & dental coverage

Stock programs & RSUs

Relocation assistance

Tuition reimbursement

Job summary

Apple Inc. is seeking an On-Device ML Infrastructure Engineer focused on Core ML Runtime to advance graph compilation, runtime systems, and ML operator primitives for on-device execution.

You will work across compiler technologies, system software, and hardware integration to deliver efficient ML models on Apple devices. You will architect and maintain on-device graph compiler, runtime, and kernels; optimize for performance, energy, and thermal constraints; collaborate with ML, OS, and hardware

Qualifications

• Masters or equivalent in CS/Engineering or related field.
• Proficient in C++ or Swift; familiarity with Python.
• Experience with compiler stacks (MLIR/LLVM/TVM).
• Understanding of OS, embedded programming, and parallel programming.
• Strong ML fundamentals, incl. transformers.
• Good communication across multi-functional audiences.

Responsibilities

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

Skills

C++

Swift

Python

ML fundamentals

Transformer models

Multi-functional communication

Education

Masters or equivalent in CS/Engineering

Job description

Apple Inc. is seeking an On-Device ML Infrastructure Engineer focused on Core ML Runtime to advance graph compilation, runtime systems, and ML operator primitives for on-device execution.

You will work across compiler technologies, system software, and hardware integration to deliver efficient ML models on Apple devices. You will architect and maintain on-device graph compiler, runtime, and kernels; optimize for performance, energy, and thermal constraints; collaborate with ML, OS, and hardware