ML Framework (MetalLM) Engineer, Graphics, Game and ML
Core
Building scalable, efficient, production-grade ML inference frameworks for GenAI applications (LLMs) on Apple Silicon server hardware.
Role type
Senior IC ML Framework Engineer (GPU/Graphics)
Builds
Custom-built server ML inference frameworks for Private Cloud Compute
Domain
Server ML, GPU programming, Apple Silicon
Deliverable
production ML models
Required skills
C/C++/ObjC, GPU kernel development, distributed inference techniques, system-level programming, computer architecture
Preferred skills
Graph compilers (CuTE, CuTile, Triton, OpenXLA, LLVM), LLM/Diffusion model architectures
Responsibilities
Optimize code for efficient/scalable ML inference using distributed compute strategies; Develop kernel and compiler-level optimizations; Apply model optimization techniques (speculation, quantization, compression); Collaborate with hardware/compiler/systems teams; Analyze and improve performance metrics (latency, memory footprint, compute efficiency)
Seniority
Senior, hands-on IC
