AMD - San Jose, CA

posted 6 months ago

Full-time - Mid Level
San Jose, CA
Computer and Electronic Product Manufacturing

About the position

At AMD, we are committed to transforming lives through our technology, and we are looking for a skilled and experienced engineer to join our core team. This role involves developing a cutting-edge machine learning model compiler specifically targeting AMD Inference Accelerator (AIE) hardware devices. The compiler will be responsible for taking models written in popular frameworks such as PyTorch, TensorFlow, ONNX, or JAX and producing optimized control and executable code for the AIE VLIW processor array. Additionally, the compiler must efficiently handle the partitioning of tasks between x86 and hardware accelerators, generate optimal code for AMD x86 CPUs using AMD ZenDNN, and create code that interfaces with the AMD AIE-specific runtime and driver. The ideal candidate will be passionate about implementing and improving effective algorithms and techniques to enhance compiler and runtime for machine learning. This position requires strong leadership skills to drive complex issues to resolution and the ability to communicate effectively while collaborating with various teams across AMD. The role also involves mentoring and providing guidance to others, learning the latest industry trends, and bringing innovative ideas to the team. You will be responsible for designing and developing groundbreaking AMD technologies, debugging and fixing existing issues, and researching alternative, more efficient methods to accomplish tasks. Building technical relationships with peers and partners is also a key aspect of this role.

Responsibilities

  • Implement and improve passes in the compiler
  • Integrate compiler and compiled model with ML Frameworks (such as PyTorch and TensorFlow)
  • Implement model partitioning in ML Frameworks and/or MLIR
  • Implement runtime to distribute work to and collect results from x86 cores and the array of AIE cores
  • Mentor and provide guidance to others
  • Learn latest industry trends and bring new ideas to the team
  • Design and develop new groundbreaking AMD technologies
  • Debugging/fix existing issues and research alternative, more efficient ways to accomplish the same work
  • Develop technical relationships with peers and partners

Requirements

  • Strong object-oriented programming background in C/C++ and Python
  • Experience with ML Compiler and Runtime technologies such as OneDNN, MLIR, XLA, OpenXLA, IREE, OpenAI Triton compiler
  • Compiler building skills
  • Code generation for a ML hardware accelerator
  • GPU code generation
  • Machine Learning concepts and model development experience
  • Understanding of PyTorch, TensorFlow, ONNX, JAX, etc.
  • Ability to write high quality code with keen attention to detail
  • Experience with modern concurrent programming and threading APIs
  • Experience with software development processes and tools such as debuggers, source code control systems (GitHub), and profilers is a plus
  • Effective communication and problem-solving skills
  • Motivating leader with good interpersonal skills
  • Bachelor's, Master's or PhD degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent

Benefits

  • Base pay depending on skills, qualifications, experience, and location
  • Eligibility for incentives such as annual bonuses or sales incentives
  • Opportunity to own shares of AMD stock
  • Discount when purchasing AMD stock through Employee Stock Purchase Plan
  • Competitive benefits package
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service