Job Description

Job Title:  HPC Middleware Engineer, System, NSCC

Requisition ID:  599
Posting Start Date:  02/11/2026

Job Summary

The HPC Middleware Engineer is responsible for installing, maintaining and supporting the software layer between the Linux operating system and user applications on NSCC's HPC and AI systems. This includes compilers, libraries, runtime environments and container platforms.


Roles and Responsibilities

  1. Middleware Stack Management

    • Compile, install and maintain HPC and AI middleware stacks on Linux-based systems, including compilers, libraries and runtime environments.

    • Compile software from source and validate builds across different compilers and optimisation options.

    • Deploy and support container platforms for HPC and AI workloads.

    • Work with System and Storage Engineers to ensure middleware compatibility with the OS, drivers, job scheduler and filesystems.

    • Ensure middleware components comply with security policies.

    2. User Support

    • Support users in compiling and running their applications on the HPC systems.

    • Troubleshoot software and environment issues affecting user jobs.

    • Provide guidance and documentation on middleware usage.

    3. Designing and Planning

    • Evaluate new middleware technologies.

    • Contribute to the design and planning of future HPC and AI systems.

Qualifications:

• Degree in Computer Science, Engineering, or a related field.

• At least 2 years of relevant experience in HPC, AI, or IT infrastructure.

• Comfortable using Linux daily, with hands-on experience configuring and troubleshooting software.

• Hands-on experience compiling and installing software from source on Linux with GCC, Make and CMake, including testing builds with different compiler optimisation flags.

• Good understanding of either an HPC middleware stack (e.g. MPI, compilers, scientific libraries) or an AI middleware stack (e.g. CUDA, PyTorch, inference and serving frameworks), with a willingness to learn the other.

• Working experience with container technologies (e.g. Docker, Podman, Singularity/Apptainer) and/or Kubernetes, for HPC/AI or other workloads such as microservices.

• Proficient in scripting with Python, Bash, or similar languages.

• Strong analytical and problem-solving skills.

Good to Have

• Experience with GPU computing or AI infrastructure.

• Familiarity with high-speed networking (e.g. InfiniBand, RoCE) or parallel file systems.

The above eligibility criteria are not exhaustive. A*STAR may include additional selection criteria based on its prevailing recruitment policies. These policies may be amended from time to time without notice. We regret that only shortlisted candidates will be notified.