Senior Performance Software Engineer, Deep Learning Libraries

Details

We are looking for a Senior Performance Software Engineer for Deep Learning Libraries to develop optimized code that accelerates linear algebra and deep learning operations on NVIDIA GPUs.

Responsibilities

• Write highly tuned compute kernels, mostly in C++ CUDA, for core deep learning operations such as matrix multiplies, convolutions, and normalizations
• Follow general software engineering best practices including support for regression testing and CI/CD flows
• Collaborate with teams across NVIDIA including:
  • CUDA compiler team for generating optimal assembly code
  • Deep learning training and inference performance teams for optimization needs
  • Hardware and architecture teams on programming models for new deep learning hardware features

Requirements

• Masters or PhD degree or equivalent experience in Computer Science, Computer Engineering, Applied Math, or related field
• 6+ years of relevant industry experience
• Strong C++ programming and software design skills, including debugging, performance analysis, and test design
• Experience with performance-oriented parallel programming (e.g., OpenMP, pthreads), even if not on GPUs
• Solid understanding of computer architecture and some experience with assembly programming

Preferred Qualifications

• Experience tuning BLAS or deep learning library kernel code
• CUDA or OpenCL GPU programming
• Knowledge of numerical methods and linear algebra
• Familiarity with LLVM, TVM tensor expressions, or TensorFlow MLIR

Benefits

• Competitive base salary range: 184,000 USD - 356,500 USD
• Eligibility for equity and benefits
• Work at NVIDIA, a leading technology company fostering diversity and innovation

Join the team that builds software underpinning AI breakthroughs in image classification, speech recognition, and natural language processing. Work on cutting-edge GPU efficiency and deep learning software stacks.