ML Software Engineer, London
Core
Engineer continuous improvements in stability and performance for private cloud compute and implement new generative AI functionality on Apple Silicon.
Role type
Senior IC ML Software Engineer (Inference)
Builds
ML-inference applications and services on Apple Silicon for the Private Cloud Compute component of Apple Intelligence.
Domain
Cloud computing + Generative AI + Apple Silicon hardware
Deliverable
production ML models
Required skills
Swift, C++, C, distributed systems, machine learning model evaluation, service stack integration, hardware acceleration coordination
Preferred skills
Apple ML stack (ANE, CoreML, MPS/Metal), PyTorch-distributed, NCCL, high-throughput inter-chip communication, on-device iOS development
Technologies
Swift, C++, C, PyTorch, NCCL, CoreML, MPS, Metal, XCode
Responsibilities
Produce reliable, maintainable software; work across multiple levels of abstraction; integrate inference code into a full service stack; develop code that is easy and safe to develop, update, and monitor.
Seniority
Senior, hands-on IC