On-Device ML Compiler Engineer: MLIR for Hardware

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

Job summary

Apple Inc. in Cupertino, California, is seeking an On-Device ML Compiler Engineer to advance the MLIR-based compiler stack, enabling efficient execution of ML models across Apple devices—from Apple Watch to Mac Ultra SoCs.

The role focuses on model compilation, runtime optimization, and tight collaboration with hardware and performance teams to harness the full capabilities of Apple silicon for private, local AI inference.

Qualifications

• 3–5 years working on MLIR-based compilers.
• Familiarity with common ML model architectures, execution schemes, and operations.
• Familiarity with C++.
• Familiarity with PyTorch or related training frameworks.

Responsibilities

• Inspire changes in our MLIR-based compiler to target improved runtime performance across devices.
• Propose upstream MLIR changes to support new hardware features and workflows.
• Own core pieces of the compiler stack enabling heterogeneous compute from watches to Macs.
• Collaborate with hardware, software, and performance teams to optimize execution on latest hardware, OS, and drivers.

Skills

MLIR compiler

C++

PyTorch

ML model architectures

Tools

MLIR

Swift

Job description

Apple Inc. in Cupertino, California, is seeking an On-Device ML Compiler Engineer to advance the MLIR-based compiler stack, enabling efficient execution of ML models across Apple devices—from Apple Watch to Mac Ultra SoCs.

The role focuses on model compilation, runtime optimization, and tight collaboration with hardware and performance teams to harness the full capabilities of Apple silicon for private, local AI inference.