职位&公司对比

职位详情

• 北京
• 3-5年
• 硕士
• 日结

• 深度学习
• 大模型算法
• 自然语言处理算法
• 模型加速/性能优化
• C/C++
• 算法工程化经验
• 发表算法相关优秀论文

THE ROLE: AMD 直聘is looking for an influential software engineer who is passionate about improving the performance of key applications and benchmarks. You will be a member of a core team of incredibly talented industry specialists and will work with the very latest hardware and software technology.  THE PERSON: The ideal candidate should be passionate about software engineering and possess leadership skills to drive sophisticated issues to resolution. Able to来自BOSS直聘 communicate effectively and work optimally with different teams across AMD. KEY RESPONSIBILITIES: Research and develop CNN/LLM compression algorithms, focusing on quantization and pruning Develop neural network compression tool chain, connecting software and hardware Stay up to date with the latest neural network compression algorithm trends and deep learning framework (Pytorch,ONNXRuntime) trends PREFERRED EXPERIENCE: Good knowledge of machine learning/deep learning, including CNN/LLM 来自BOSS直聘Experience in at least one deep learning framework, such as Pytorch, ONNXRuntime At least 3 years’ experience in BOSS直聘C++ or Python programming under Linux Fluent English communication with native speaker With research, creativity, and ability to learn the cutting-edge algorithms and theories through paper reading Expekanzhunrience in academic papers is preferred, such as CVPR, ICCV, ECCV, NIPS, ICLR,TPAMI Experience in CNN/LLM model compression algorithms is preferred ACADEMIC CREDENTIALS: Master's or Doctor's degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent