AI Engineer, Deep Learning and Inference Optimization at Intel

Intel is hiring a college graduate AI engineer in Shanghai to develop and optimize high-performance deep learning solutions for Intel accelerators and customer frameworks. The role includes performance optimization, debugging accuracy and memory issues, designing model deployment architectures, implementing inference acceleration features in vLLM or SGLang, developing high-performance kernels, and collaborating with engineering stakeholders. A master's or Ph.D. in computer science, artificial intelligence, software engineering, or a related field is required, along with strong C++ and Python programming, deep learning knowledge, English proficiency, and problem-solving ability. Experience with LLMs/AIGC, PyTorch, vLLM, SGLang, or GPU kernel development is preferred.