Machine Learning Engineer, Foundation Model Services
Core
Build frameworks, services, and tools to power Apple's largest foundation models (language, vision, speech) at scale for products like Siri, Apple Search, and Apple Music.
Role type
Senior IC machine learning engineer (foundation model services)
Builds
Production-grade inference services and tools for billion-parameter models
Domain
Consumer technology, large-scale AI infrastructure
Deliverable
production ML models
Required skills
LLMs, NLP, Information Retrieval, Statistics, high-throughput services, supercomputing scale, Cloud (AWS/Azure), Kubernetes, Docker, Golang, Python
Preferred skills
PyTorch, TensorFlow, Transformers, Encoder/Decoder models, Nvidia TensorRT-LLM, vLLM, DeepSpeed, Nvidia Triton Server
Responsibilities
Work with product teams to build production-grade solutions for real-time model serving; collaborate with research teams to prototype inference for cutting-edge architectures; build tools to analyze inference bottlenecks across different hardware and use cases
Seniority
Senior, hands-on IC