Server ML Frameworks Engineer
Core
Senior technical leader defining software architecture and technical direction for high-performance, distributed inference of GenAI applications (LLMs) on Apple's Private Cloud Compute using custom server hardware.
Role type
Senior IC/Technical Lead Server ML Frameworks Engineer
Builds
Scalable, production-grade server-side ML frameworks and optimized GPU compute kernels for Apple Intelligence
Domain
Cloud computing, Generative AI, GPU architecture, High-performance computing
Deliverable
production ML models
Required skills
GPU kernel development and optimization, Distributed training/inference, System-level programming (C/C++), Compiler and kernel optimization, Metal Performance Shaders API, Hardware-software co-design
Preferred skills
Strategic leadership, Apple framework/API design patterns, Graph compilers (CuTE, CuTile, Triton, OpenXLA, LLVM), LLM and Diffusion model architectures
