HPC Middleware Engineer, System, NSCC

Agency for Science, Technology and Research (A*STAR); Singapore; On-site; SGD 70,000 - 90,000; Full time

Job summary

A leading research agency in Singapore is seeking an HPC Middleware Engineer responsible for deploying and optimizing middleware components in a high-performance computing environment. This role involves collaborating with engineers to ensure middleware compliance and supporting users with application integration and performance tuning. Ideal candidates should have a degree in computer science or engineering and at least 3 years of relevant experience, with a deep proficiency in Linux systems and container technologies.

Qualifications

• Minimum 3 years of experience in HPC environments, focusing on middleware or application integration.
• Proficient with container technologies and HPC programming suites.
• Strong knowledge of middleware stack management in HPC.

Responsibilities

• Deploy, configure, and maintain the HPC middleware stack.
• Assist users in integrating applications with middleware.
• Evaluate new middleware technologies and contribute to architecture design.

Skills

Linux systems

MPI (Cray MPI, OpenMPI, MPICH)

Scientific libraries (Intel MKL, cuBLAS)

I/O libraries (HDF5, NetCDF)

Container technologies (Singularity, Enroot, Podman)

Scripting skills (Python, Bash, Perl)

Analytical and troubleshooting abilities

Education

Degree in Computer Science, Engineering, or related field

Tools

HPC programming suites (Intel OneAPI, NVHPC)

RDMA-based interconnects (InfiniBand, RoCE)

Parallel file systems (Lustre, GPFS, BeeGFS)

Job description

Job Summary

The HPC Middleware Engineer is responsible for deploying, optimizing, and supporting middleware components in a high-performance computing (HPC) environment. This includes scientific libraries, compilers, runtime environments, and container technologies that bridge system software and user applications. The role supports efficient application performance and seamless integration across the HPC stack.

Roles and Responsibilities

• Middleware Stack Management
  • Deploy, configure, and maintain the HPC middleware stack, which includes scientific libraries and frameworks, HPC runtime environments.
  • Manage and support container engines for HPC workloads.
  • Collaborate with HPC System and Storage Engineers to ensure middleware compatibility with OS, drivers, scheduler, and filesystems.
  • Ensure middleware components comply with security policies.
• Application Integration and Support
  • Assist users in integrating domain-specific applications with middleware layers to ensure optimal performance and compatibility.
  • Assist in tuning and troubleshooting through performance profiling and debugging.
  • Provide technical guidance to users on middleware usage and best practices.
• Designing and Planning
  • Evaluate new middleware technologies and programming models.
  • Contribute to middleware architecture design for future HPC expansions.

Qualifications

• Degree in Computer Science, Engineering, or related field.
• Minimum 3 years of experience in HPC environments, with focus on middleware or application integration.
• Proficient in Linux systems and CLI tools.
• Strong knowledge of MPI (Cray MPI, OpenMPI, MPICH), scientific libraries (Intel MKL, cuBLAS), and I/O libraries (HDF5, NetCDF).
• Experience with container technologies (Singularity, Enroot, Podman) and HPC programming suites (Intel OneAPI, NVHPC).
• Familiarity with RDMA-based interconnects (InfiniBand, RoCE) and parallel file systems (Lustre, GPFS, BeeGFS).
• Scripting skills in Python, Bash, or Perl.
• Strong analytical and troubleshooting abilities.