DevJobs

AI/ML Acceleration Senior Software Engineer

Overview
Skills
  • C C
  • Kernel drivers
  • Kernel programming
  • Libfabric
  • NCCL
  • ARMv8 architecture
  • PCIe protocol
  • RoCE
  • TCP/IP
  • Virtualization technologies

Xsight Labs is seeking a highly skilled senior software engineer to join our dynamic team. The ideal candidate will be responsible for developing AI/ML acceleration drivers and software for cutting-edge AI networking technology.


Responsibilities

  • Work on implementing a cutting-edge standard for AI networking, revolutionizing next-generation infrastructure for Generative AI training clusters.
  • Design, implement and test drivers for hardware acceleration, enabling distributed AI/ML applications.
  • Collaborate with a diverse team of system/software architects, hardware designers, and system/test engineers.
  • Collaborate with open-source communities.

Requirements

  • BSc or MSc in computer science or computer engineering, or equivalent experience
  • 7+ years of experience in software development.
  • Developing and running GPU-accelerated HPC or AI related applications.
  • Background with HPC or AI/ML cluster networking.
  • Hands-on experience with Collective Communication Libraries (e.g., NCCL) and Libfabric.
  • Solid knowledge of kernel programming and kernel drivers.
  • Strong programming skills in C.

Advantages

  • Knowledge and experience of networking and/or RDMA protocols (e.g., TCP/IP, RoCE).
  • Familiarity with PCIe protocol and virtualization technologies.
  • Experience with ARMv8 architecture.
  • Contributions to HPC or AI/ML related open-source projects.

Xsight Labs