C

Cornelis Networks

High-speed AI/HPC networking fabrics

Software Engineer - AI/HPC Middleware

Software EngineeringConfirmed live in the last 24 hours
Full-timeRemote in USANo salary listed

About the Job

Requirements

  • At least 2 years of experience in systems programming in C/C++ on Linux; a bachelor's degree in Computer Science, Engineering, or a related field, or equivalent experience.
  • Exposure to or coursework or project experience with HPC middleware such as MPI/SHMEM, AI collective communication libraries such as NCCL/RCCL and CUDA/ROCm, or other collective communication stacks.
  • Familiarity with performance concepts and the ability to diagnose issues using profiling or tracing tools, or a strong willingness to learn.
  • Foundational understanding of networking or RDMA concepts.

Responsibilities

  • Implement and help optimize features for HPC middleware (HPI and SHMEM) and AI middleware stacks, including NCCL/RCCL and related collective communication libraries.
  • Assist in integrating middleware capabilities with underlying transports and provider layers, including libfabric/OFI, UCX, and verbs-like semantics where applicable.
  • Prepare and submit upstream contributions across MPI/SHMEM projects, collective communication ecosystems, and related components.
  • Collaborate with kernel/driver and switch teams to help deliver end-to-end performance aligned to the product roadmap.
  • Help analyze performance traces, reproduce customer issues, and assist in translating findings into fixes.

Desired Qualifications

  • A master's degree or doctorate.
  • Experience contributing to open-source projects.
  • Exposure to libfabric providers.
  • Familiarity with Ultra Ethernet (UEC/UET) specifications.
  • Experience with RoCEv2, congestion control, or Ethernet-based RDMA deployments.
  • Experience with benchmarking, profiling, and optimization.
  • Background with Omni-Path/OPX or Ethernet-based HPC fabrics.

About the Company

Cornelis Networks

High-speed AI/HPC networking fabrics

Cornelis Networks builds high-performance AI and HPC networking fabrics to help accelerators and servers in data centers exchange data with less idle GPU time. Its open architecture works across different GPUs and accelerators, avoiding vendor lock-in and not relying on a single full-stack solution. The company began shipping products after spinning out of Intel in 2020 and is developing a next-generation fabric. Its current push includes Active Compute Fabric, a networking technology that lets chips process and send information concurrently, aimed at enabling closer integration of compute and communication. The goal is to commercialize the platform, expand adoption, and challenge closed AI networking stacks by offering an open, multi-vendor fabric that improves data movement in AI/HPC clusters.

Company size
201-500
Company stage
Late Stage VC
Total funding
$335.8M
Headquarters
Tredyffrin Township, Pennsylvania
Founded
2019

Recently Posted Jobs

Explore more opportunities at Cornelis Networks

See more jobs