Description
Apple is hiring an ML Inference Engineer to build and improve the stability, performance, and scalability of its distributed ML-inference stack for Private Cloud Compute. The role involves writing performant Swift and C++ frameworks that coordinate inference across SoC acceleration hardware and multi-node clusters, integrating inference code into a full service stack, and collaborating with hardware, product, and research teams. Candidates need at least two years of practical experience, a relevant bachelor's degree or equivalent experience, and experience with large-scale distributed systems serving ML inference.
