AI/Machine Learning Engineer (Embedded Systems, Inference Efficiency)
Core
Conduct advanced research on model efficiency, compression, and ML system optimization to enable efficient on-device inference for Qualcomm AI accelerators.
Role type
Senior IC machine learning engineer (embedded systems, inference efficiency)
Builds
Low-power AI solutions and production-ready model deployment for Qualcomm AI accelerators
Domain
Semiconductor / Embedded AI / Hardware-Software Co-design
Deliverable
production ML models
Required skills
Neural network architecture design, model compression (quantization, pruning, knowledge distillation), compiler stack optimization (graph transformation, tiling, scheduling), ML system optimization, ML framework programming, model development pipelines (training, fine-tuning, evaluation)
Preferred skills
PhD in CS/EE or MS with AI research, publications in top-tier ML venues (NeurIPS, ICML, ICLR, CVPR), on-device model deployment experience, experience with AI hardware accelerators
Technologies
ML frameworks, Qualcomm AI accelerators, compiler stacks
Responsibilities
Design efficient architectures and optimize compilers for AI accelerators, prototype software-hardware co-design solutions, collaborate with hardware and modeling teams to convert research into production solutions, influence future accelerator features
Seniority
Senior, hands-on IC
