Machine Learning Engineer – PyTorch / C++ / NPU ArchitectureWe are partnered with a global semiconductor leader seeking a Machine Learning Engineer to join their NPU Architecture Team. This is a chance to shape the future of energy-efficient ML technology used in billions of devices worldwide.What you'll be doing:Develop and enhance ML compilers using PyTorch and C++ for advanced NPU architectureDesign and implement quantization techniques to improve model efficiency and accuracyOptimize ML workloads for high performance and low power consumptionCollaborate with strategic customers to deliver tailored ML solutionsPartner with architecture and software teams to integrate new ML technologiesResearch, prototype, and implement compiler and system-level optimizationsWhat we're looking for:Strong background in PyTorch and C++ programmingExperience in ML compiler development, quantization, and workload analysisFamiliarity with TensorFlow or ONNX a plusSolid understanding of hardware-aware ML solutions and performance optimizationExcellent problem-solving, collaboration, and communication skillsPreferred:Experience deploying ML models on NPUs, GPUs, or TPUsUnderstanding of system-level architecture and low-level programmingResearch or publications in ML-related fieldsIf this sounds interesting and you'd like to learn more, click the link below to apply or email me with a copy of your CV on-By applying to this role you understand that we may collect your personal data and store and process it on our systems. For more information please see our Privacy Notice (https://eu-)