ML Software Engineer, London
Core
Building ML-inference applications and services on Apple Silicon in the datacenter, specifically focusing on generative AI for Apple Intelligence.
Role type
ML Software Engineer (Inference & Private Cloud Compute)
Builds
ML-inference services and frameworks for Apple Silicon datacenter
Domain
Consumer electronics, Generative AI, Cloud Infrastructure
Deliverable
production ML models
Required skills
Swift, C++, C, distributed ML stack (PyTorch-distributed, NCCL), Apple ML stack (ANE, CoreML, MPS/Metal), high-throughput inter-chip communication, on-device iOS development
Preferred skills
Experience with large production systems, experience running and evaluating ML models
Technologies
Apple Silicon, Swift, C++, PyTorch, NCCL, CoreML, MPS, Metal, XCode
Responsibilities
Engineer continuous improvements in stability and performance for private cloud compute, implement new functionality from research, integrate inference code into a full service stack
Seniority
Mid-to-Senior, hands-on IC