ML Framework Engineer (MetalLM) for GPU Inference

Apple Inc.; Cupertino (CA); On-site; USD 147,400 - 272,100; Full time

Benefits offered by this job

Employee stock purchase plan

Comprehensive medical and dental coverage

Educational expense reimbursement

Relocation assistance

Job summary

Apple Inc. in Cupertino, California, is seeking an experienced ML Framework Engineer to join their Server ML Frameworks team. This role focuses on enabling Apple Intelligence through high-performance ML applications and involves working on custom-built server hardware for distributed inference.

The ideal candidate will have a strong programming background and expertise in GPU compute, with responsibilities including optimizing ML frameworks and collaborating on GPU architecture design. Competitive benefits and pay are offered.

Qualifications

• 3+ years of programming experience with C/C++/ObjC.
• Experience with GPU kernel optimizations.
• Knowledge of distributed training and inference techniques.

Responsibilities

• Optimize ML inference code for efficiency and scalability.
• Develop kernel and compiler level optimizations.
• Collaborate closely with hardware and compiler teams.

Skills

Programming with C/C++/ObjC

GPU kernel development

Distributed training/inference

System-level programming

Tools

Metal

CUDA

LLVM

Job description

Apple Inc. in Cupertino, California, is seeking an experienced ML Framework Engineer to join their Server ML Frameworks team. This role focuses on enabling Apple Intelligence through high-performance ML applications and involves working on custom-built server hardware for distributed inference.

The ideal candidate will have a strong programming background and expertise in GPU compute, with responsibilities including optimizing ML frameworks and collaborating on GPU architecture design. Competitive benefits and pay are offered.