Machine Learning Engineer, Foundation Model Services
Core
Build production-grade solutions and inference services for Apple's largest foundation models (LLMs, vision, speech) serving millions of queries at low latency across products like Search, Siri, and the App Store.
Role type
Senior IC machine learning engineer (foundation model services)
Builds
Production inference services and tools for large-scale foundation models
Domain
Consumer technology + Large Language Models (LLMs) + Speech & Vision
Deliverable
production ML models
Required skills
Go or Python, Cloud platforms (AWS/Azure/GCP), Containers and Kubernetes/Docker, High-throughput low-latency service architecture, LLMs/NLP/Information Retrieval/Statistics
Preferred skills
Nvidia TensorRT-LLM, vLLM, DeepSpeed, Nvidia Triton Server
