Senior HPC Middleware Engineer — Hybrid

Intel; Austin (TX); Hybrid; USD 129,000 - 245,000; Full time

Job summary

Intel is seeking a Senior Cloud Software Development Engineer to advance the oneCCL library for data center HPC. You will work on the Aurora supercomputer collaboration with Argonne National Labs, focusing on cutting-edge communication libraries and performance optimizations.

Join a team developing high-performance software for Intel GPUs/CPUs, targeting low latency and high reliability across distributed systems in a data-center/HPC environment.

Qualifications

• Master's degree or higher in CS/CE or STEM field.
• 3+ years of software development experience.
• 3+ years of Linux environment development experience.
• 3+ years of C/C++ programming experience.
• Experience with multithreaded programming and parallel computing concepts.
• Specialized Experience (at least one): Distributed computing, HPC communications libraries, MPI/oneCCL/NCCL/SHMEM, GPU programming, or network stack development.

Responsibilities

• Develop and optimize the oneCCL communication library and related features.
• Design, develop, and maintain advanced features and performance optimizations.
• Optimize software for low latency, high bandwidth, and high reliability.
• Implement and enhance communication protocols across the software stack.

Skills

Multithreaded programming

Distributed computing

High-performance computing

GPU software development

Network communications stacks

Education

Master's degree in Computer Science/Computer Engineering or STEM field

Ph.D. degree (preferred)

Tools

C and C++ programming

Linux development

MPI / oneCCL / NCCL / SHMEM

GPU architectures

Job description

Intel is seeking a Senior Cloud Software Development Engineer to advance the oneCCL library for data center HPC. You will work on the Aurora supercomputer collaboration with Argonne National Labs, focusing on cutting-edge communication libraries and performance optimizations.

Join a team developing high-performance software for Intel GPUs/CPUs, targeting low latency and high reliability across distributed systems in a data-center/HPC environment.