Lead/staff Ai-ml Software Engineer

AMD AMD · Semiconductors · Hyderabad, India · Engineering

Lead/Staff AI-ML Software Engineer at AMD responsible for developing and optimizing AI/ML specific C/C++ kernels and dataflow schedules for AMD Ryzen Processors with XDNA NPUs, focusing on mapping LLMs and Stable Diffusion networks. The role involves vector processor optimization, performance profiling, tuning, testing, and validation.

What you'd actually do

  1. Develop AI/ML specific C/C++ kernels and dataflow schedules for AMD Ryzen Processors built on XDNA Neural Processor Units (NPU) to map LLMs, Stable Diffusion networks on NPU.
  2. Optimize and implement machine learning kernels specifically tailored for vector processors.
  3. Perform performance profiling and tuning to enhance efficiency, speed, and accuracy of machine learning models.
  4. Conduct testing and validation of developed kernels and optimizations.
  5. Create documentation and collaborate with cross-functional teams.

Skills

Required

  • Excellent C/C++ and Python coding skills
  • Good understanding of SIMD/Tensor/VLIW processor architecture to exploit parallelism.
  • Experience with vectorized programming (SIMD) and parallel computing.
  • Excellent problem-solving skills and a passion for performance optimization.

Nice to have

  • Familiarity with machine learning frameworks (e.g., TensorFlow, PyTorch) is a plus.
  • Experience with silicon bring-up and pre-silicon validation on Emulation platforms is a plus.
  • Knowledge of low-level hardware details (cache hierarchy, memory access patterns) is desirable.

What the JD emphasized

  • AI/ML specific C/C++ kernels
  • XDNA Neural Processor Units (NPU)
  • LLMs
  • Stable Diffusion networks
  • Vector Processor Optimization
  • Performance Profiling and Tuning

Other signals

  • Developing AI/ML specific C/C++ kernels
  • mapping LLMs, Stable Diffusion networks on NPU
  • Vector Processor Optimization
  • Performance Profiling and Tuning