Senior Software Engineer (gpu & Ai/ml)

AMD AMD · Semiconductors · Belgrade, Serbia · Engineering

Senior Software Engineer at AMD focusing on developing and optimizing AI software stack for AMD's GPU and NPU products. The role involves enabling standard AI frameworks, bringing up new AI models, analyzing performance, and participating in end-to-end development.

What you'd actually do

  1. Develop and deliver innovative AI software solutions to AMD customers and users.
  2. Enable and optimize software stack for standard frameworks like ONNX and PyTorch, as well as new popular Open-Source AI software.
  3. Bring up new SOTA AI models, analyze and improve their performance.
  4. Participate and drive end-2-end AI software development from feature scoping, implementation, integration and verification, to customer enablement.

Skills

Required

  • C/C++
  • Python
  • AI development
  • Windows
  • Linux
  • Machine Learning
  • AI accelerators
  • AI systems
  • ONNX
  • PyTorch
  • Open-Source AI software
  • performance analysis
  • feature scoping
  • implementation
  • integration
  • verification
  • customer enablement
  • cross-platform software development
  • CONV
  • GEMM
  • non-linear operators
  • AI frameworks
  • inference stacks
  • AI and ML concepts and techniques
  • compute, memory, and communication configurations

Nice to have

  • GPU
  • NPU
  • GPU acceleration
  • Open-source software development

What the JD emphasized

  • strong technical and analytical skills in C/C++/Python AI development
  • knowledge on GPU or NPU
  • technical leader to define goals and scope and drive development effort
  • experience in Machine Learning or AI accelerators or systems
  • develop our latest AI software technologies
  • optimize various parts of the AI software stack
  • deliver AI solutions across AMD Radeon and Ryzen product families
  • Bring up new SOTA AI models
  • analyze and improve their performance
  • end-2-end AI software development
  • feature scoping, implementation, integration and verification
  • customer enablement
  • Strong cross-platform software development experience
  • deep programming skills in C/C++ and Python
  • Development experience on CONV, GEMM, and/or non-linear operators
  • GPU acceleration experience
  • Experience with common AI frameworks and inference stacks
  • Solid knowledge of AI and ML concepts and techniques
  • understanding the performance implications on AI acceleration of different compute, memory, and communication configurations

Other signals

  • optimize software stack for AI
  • bring up new SOTA AI models
  • analyze and improve performance