ML Framework (MetalLM) Engineer

Apple • Cupertino, CA

5d

About The Position

Apple’s ML Frameworks (MetalLM) team in GPU, Graphics and Machine Learning works on enabling Apple Intelligence through high-performance, distributed inference of GenAI applications (such as LLMs) on Private Cloud Compute. You will get to work on custom-built server hardware that brings the power and security of Apple silicon to the data center. Team also works on GPU acceleration of ML Training frameworks such as PyTorch and JAX using Metal runtime and device backend. We are looking for engineers with systems background who are deeply passionate about building scalable, efficient, and production-grade solutions tailored for high-throughput GPU execution.

Requirements

• 3+ years of programming and problem-solving experience with C/C++/ObjC
• Experience with GPU kernel development & optimizations using compute programming models such as Metal, CUDA etc.
• Experience with system level programming and computer architecture
• Experience with Distributed training or inference techniques

Nice To Haves

• Experience with graph compilers such as Triton, OpenXLA or LLVM/MLIR is a plus
• Contributions to an AI framework such as PyTorch, JAX or Tensorflow is a plus
• Good understanding of machine learning fundamentals

Responsibilities

• Work on cutting-edge ML inference framework project and optimize code for efficient and scalable ML inference using distributed compute strategies such as data, tensor, pipeline and expert parallelism.
• Develop kernel and compiler level optimizations and perform in-depth analysis to ensure the best possible performance across Server hardware families.
• Apply advanced model optimization techniques including speculation, quantization, compression, and others to maximize throughput and minimize latency.
• Collaborate closely with hardware, compiler, and systems teams to align software performance with hardware capabilities.
• Analyze and improve performance metrics such as end-to-end latency, TTFT, TBOT, memory footprint, and compute efficiency.
• Implement features of Metal device backend for ML training acceleration technologies

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed