ML Deployment Engineer, Edge AI - Q
Core
Deploy and optimize machine learning models for efficient on-device execution on Apple silicon, ensuring performance, power, and privacy for millions of users.
Role type
Senior IC ML Deployment Engineer (Edge AI)
Builds
Production-ready on-device AI features running on Apple Neural Engine, GPU, and CPU
Domain
Consumer electronics / Edge AI / Hardware-accelerated inference
Deliverable
production ML models
Required skills
Model compression (quantization, pruning, palettization), Graph compilation, Hardware-aware optimization, Python, C/C++, Deep learning frameworks (PyTorch), Profiling and benchmarking, Debugging at ML/hardware boundary
Preferred skills
Apple Neural Engine (ANE) expertise, Core ML and MLIR, Compiler analytics, Low-level compute kernels, SoC memory hierarchies, On-device LLMs
Technologies
Core ML, PyTorch, ONNX Runtime, TensorRT, TFLite, MLIR, GPTQ
Responsibilities
Own end-to-end model deployment pipeline from checkpoint to on-device execution; Apply model compression techniques and validate trade-offs; Convert and compile models to target silicon; Analyze and maximize accelerator residency; Profile and optimize inference for latency, memory, and energy; Collaborate with research teams to co-design efficient models; Build automation tooling for compression and validation
Seniority
Senior, hands-on IC
