Deep Learning Performance Software Engineer

NVIDIA NVIDIA · Semiconductors · Beijing, China +1

NVIDIA is seeking a Deep Learning Performance Software Engineer to develop compilers and DSLs for deep learning workloads, design and implement optimized deep learning kernels, improve compiler architecture, and perform performance analysis on AI workloads. Requires a Master's or Ph.D. degree, excellent C/C++ skills, and experience with tools like XLA, TVM, MLIR, LLVM, and deep learning models.

What you'd actually do

  1. Develop compilers and DSLs for deep learning workloads
  2. Design and implement highly optimized deep learning kernels
  3. Continuously improve the compiler architecture for current and next generation chips
  4. Perform performance analysis on emerging AI workloads and integrate with AI frameworks

Skills

Required

  • Master's or Ph.D degree (or equivalent experience) in relevant discipline (CE, CS&E, CS, AI)
  • Excellent C/C++ programming and software design skills
  • Experience with XLA, TVM, MLIR, LLVM, deep learning models and algorithms
  • 3+ years of relevant work experience

What the JD emphasized

  • ability to work in a fast-paced customer-oriented team is required
  • excellent communication skills are necessary

Other signals

  • GPU-accelerated Deep learning software
  • deep learning kernels
  • AI frameworks