On-Device ML Compiler Engineer for Apple Silicon

Apple; Cupertino (CA); On-site; USD 120,000 - 150,000; Full time

Job summary

Apple is looking for an ML Infrastructure Engineer to join its On-Device Machine Learning team in Cupertino, California. This role involves enhancing the MLIR-based compiler and collaborating with various teams to optimize execution across Apple devices. The ideal candidate has strong experience in compiler optimization, familiarity with machine learning frameworks, and deep knowledge of software fundamentals.

As part of a dynamic environment, you will contribute to transformative AI applications while working closely with cutting-edge technology, making a significant impact on the future of intelligent experiences across Apple's platforms.

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 MLIR-based compiler for improved runtime performance.
• Propose changes in MLIR for better feature support.
• Own core pieces of the compiler stack for heterogeneous compute.
• Work closely with hardware and software teams for optimization.

Skills

MLIR-based compilers

C++

PyTorch

Common ML model architectures

Tools

Swift

Job description

Apple is looking for an ML Infrastructure Engineer to join its On-Device Machine Learning team in Cupertino, California. This role involves enhancing the MLIR-based compiler and collaborating with various teams to optimize execution across Apple devices. The ideal candidate has strong experience in compiler optimization, familiarity with machine learning frameworks, and deep knowledge of software fundamentals.

As part of a dynamic environment, you will contribute to transformative AI applications while working closely with cutting-edge technology, making a significant impact on the future of intelligent experiences across Apple's platforms.