北京招聘

AMD and Machine Learning

Intelligent applications that respond with human-like reflexes require an enormous amount of computer processing power. AMD’s main contributions to ML and DL systems come from delivering high-performance compute (both CPUs and GPUs) with an open ecosystem for software development. ML and DL applications rely on computer hardware that can support the highest processing capabilities (speed, capacity, and organization) to simultaneously manage complex data sets from multiple input streams.

We are now looking for a Machine Intelligence Tech Lead, what You’ll be doing but Not Limited to:

• Analyze performance of Machine Intelligence Software Development (Driver, Frameworks, Libraries)
• Identify bottlenecks and tuning opportunities and work with broader team to optimize software and hardware
• Develop tools, simulators, scripts as needed to automate process
• Work with latest machine hardware and software
• Optimize deep learning frameworks like TensorFlow, PyTorch, etc. on AMD processors
• Collaborate and interact with internal GPU library teams to analyze and optimize training and inference for deep learning
• Collaborate with open-source framework maintainers and understand and implement their requirements
• Work in a distributed computing setting to optimize for both scale-up (multi-GPU) and scale-out (multi-node) systems
• Work with cutting-edge compiler technologies
• Optimize the entire deep learning pipeline
• Apply your knowledge of software engineering best practices

Requirement

• BS or MS or PhD in Computer Science, Electrical Engineering or Mathematics
• Working experience: BS 8+ years; MS 6+ years or PhD 2+ years strongly preferred
• Strong programming skills in C or C++
• Scripting language (Python, Perl ) knowledge and UNIX/Linux experience is required
• Excellent communicator, both written and verbal
• GPU programming experience in OpenCL, CUDA, HIP, or similar
• Practical experience optimizing a GPU-accelerated program
• Understanding GPU architecture and key optimization techniques
• Experience using profiling tools and understanding performance counters
• Experience with a machine learning framework
• Strong background in compilers.
• Experience with wide variety of aspects of compiler and parallel programming
• Clang/LLVM experience
• Parallel Programming Models, Languages and Runtime Systems
• Good understanding of GPU execution model and architecture
• Experience working with a programming language committee preferred

AMD公司成立于1969年，总部位于美国加利福尼亚州桑尼维尔。AMD（NYSE: AMD）是一家创新的科技公司，致力于与客户及合作伙伴紧密合作，开发下一代面向商用、家用和游戏领域的计算和图形处理解决方案。AMD的业务遍布全球，拥有约为12000名员工。