Compute Performance Developer Technology Engineer

NVIDIA NVIDIA · Semiconductors · France · Remote

Software developer or computer scientist to join Compute Developer Technology team focusing on research and development of techniques to accelerate leading applications in scientific computing, computational engineering, data analytics, and artificial intelligence. Responsibilities include in-depth analysis and optimization for performance on CPU, GPU, and network architectures, guiding key application developers, developing reference codes or libraries, and creating/optimizing core parallel algorithms and data structures using the NVIDIA platform. The role also involves influencing next-generation architectures and software stack design.

What you'd actually do

  1. Engage directly with experts in their field to understand and address the problems they are solving today and tomorrow.
  2. Guide key application developers, contribute directly to the applications, develop reference codes or libraries.
  3. Create and optimize core parallel algorithms and data structures to provide the best solutions using the NVIDIA platform.
  4. Join efforts with diverse groups at NVIDIA such as the architecture, research, libraries, tools, system software, and product management teams to constantly improve our platform.
  5. Influence the design of next-generation architectures, software stack, and programming models, by investigating the impact on application performance and developer productivity.

Skills

Required

  • BS, MS, or PhD degree in computer science or in engineering or a domain science with a strong focus on the related computational methods or equivalent experience with 5+ years of experience
  • Strong knowledge of C/C++ and/or Fortran
  • Solid understanding in software design, programming techniques, and algorithms
  • Hands-on experience with parallel programming, e.g., in MPI, OpenMP, CUDA, and/or OpenACC
  • Good communication and organization skills
  • Logical approach to problem solving
  • Good time management and task prioritization skills
  • Fluency in French
  • French citizenship

Nice to have

  • CUDA

What the JD emphasized

  • strong knowledge of C/C++ and/or Fortran
  • hands-on experience with parallel programming, e.g., in MPI, OpenMP, CUDA, and/or OpenACC

Other signals

  • optimize performance on CPU, GPU, and network architectures
  • parallel programming
  • CUDA