MetalLM ML Framework Engineer — GPU & Server Inference

Apple; Cupertino (CA); On-site; USD 120,000 - 160,000; Full time

Job summary

Apple’s Server ML Frameworks team in Cupertino seeks engineers to optimize high-performance GenAI applications. This role focuses on ML inference framework projects and GPU programming while collaborating with cross-functional teams to enhance performance.

The ideal candidates will have over 3 years of experience in C/C++ and proficiency in GPU kernel development using Metal or CUDA. Join us to contribute to the future of Apple Silicon in the data center.

Qualifications

• 3+ years of programming experience in C/C++/ObjC.
• Experience with GPU kernel development and optimizations.
• Strong understanding of system-level programming and computer architecture.

Responsibilities

• Optimize ML inference using distributed compute strategies.
• Develop kernel and compiler level optimizations.
• Analyze and improve performance metrics.

Skills

C/C++/ObjC programming

GPU kernel development

Distributed training or inference

System-level programming

Tools

Metal

CUDA

Graph compilers (CuTE, CuTile, Triton)

Job description

Apple’s Server ML Frameworks team in Cupertino seeks engineers to optimize high-performance GenAI applications. This role focuses on ML inference framework projects and GPU programming while collaborating with cross-functional teams to enhance performance.

The ideal candidates will have over 3 years of experience in C/C++ and proficiency in GPU kernel development using Metal or CUDA. Join us to contribute to the future of Apple Silicon in the data center.