Sr. Software Development Engineer

AMD AMD · Semiconductors · Santa Clara, CA · Engineering

Sr. Software Development Engineer at AMD to research, design, develop, and/or test operating systems-level software, compilers, and/or network distribution software for semiconductor operations. The role involves developing and deploying deep learning or machine learning solutions for high-performance computing devices, debugging, performance analysis, and test design. Requires experience with C, C++, Python, AI frameworks (PyTorch, TensorFlow, vLLM), GPU computing (HIP, CUDA, OpenCL), GPU architecture, code optimization, and source code control systems.

What you'd actually do

  1. Research, design, develop, and/or test operating systems-level software, compilers, and/or network distribution software for semiconductor operations, applying principles and techniques of computer science, engineering, and mathematical analysis.
  2. Design, develop, troubleshoot and debug software programs for enhancements and new products.
  3. Develop software and tools in support of design, infrastructure and technology platforms, including operating systems, compilers, routers, networks, utilities, databases, cloud-based and Internet related tools.
  4. Determine hardware compatibility and/or influence hardware design.
  5. Work in an area of specialization to develop systems-level software, working on problems of complex scope where analysis of situations or data requires a review of a variety of factors.

Skills

Required

  • Developing and deploying deep learning or machine learning solutions for high performance computing devices
  • Performing debugging, performance analysis, and test design of software
  • C, C++, or Python
  • AI frameworks PyTorch, TensorFlow, or vLLM
  • GPU computing in HIP, CUDA, or OpenCL
  • GPU architecture and GPU programming
  • Code optimization using the GPU
  • Source code control systems in Github or profilers

What the JD emphasized

  • Developing and deploying deep learning or machine learning solutions for high performance computing devices
  • Performing debugging, performance analysis, and test design of software
  • AI frameworks PyTorch, TensorFlow, or vLLM
  • GPU computing in HIP, CUDA, or OpenCL
  • Code optimization using the GPU

Other signals

  • Developing and deploying deep learning or machine learning solutions
  • AI frameworks PyTorch, TensorFlow, or vLLM
  • GPU computing in HIP, CUDA, or OpenCL
  • Code optimization using the GPU