AI Research Engineer (Model Compression & Quantization) - 100% Remote Worldwide

Requisitos

• Degree in Computer Science or related field
• ideally PhD in NLP/ML with AI R&D track record (publications in A* conferences)
• Knowledge of Metal Shading Language (MSL)
• able to write custom compute shaders from scratch
• Proven experience in low-level kernel optimizations and inference optimization on mobile devices
• Deep understanding of modern model serving architectures and inference optimization techniques
• Strong expertise writing GPU kernels for smartphones
• deep knowledge of model serving frameworks and engines