Lead HPC Ops Engineer for Global Low-Latency Trading

Mode Talent Pty Ltd; Sydney; On-site; AUD 360,000 - 440,000; Full time

Job summary

Mode Talent Pty Ltd in Sydney is assisting a global trading firm to hire an experienced HPC Operations Engineer to maintain, optimise, and support Linux-based HPC environments powering quantitative research and low-latency trading.

You will manage large-scale HPC clusters, storage, and networking; tune Lustre/GPFS, Slurm/Grid Engine, and RDMA; automate with Ansible or SaltStack; and collaborate with research and trading teams to maximise uptime and performance.

Qualifications

• Strong Linux systems administration experience in HPC environments.
• Knowledge of parallel filesystems, batch schedulers, and high-performance networking.
• Proficiency in at least one scripting language.

Responsibilities

• Manage and support large-scale HPC clusters, storage, and networking infrastructure.
• Maintain and optimise Lustre/GPFS parallel filesystems, Slurm/Grid Engine schedulers, and RDMA fabrics.
• Diagnose and resolve complex operational issues in mission-critical environments.
• Automate processes with tools like Ansible, SaltStack, and scripting in Python, Go, or C.
• Collaborate closely with research and trading teams to ensure maximum uptime and performance.

Skills

Linux administration

HPC technologies

Scripting (Python/Go/C)

High-performance networking

Cluster management

Tools

Lustre/GPFS

Slurm/Grid Engine

RDMA fabrics

Ansible

SaltStack

Job description

Mode Talent Pty Ltd in Sydney is assisting a global trading firm to hire an experienced HPC Operations Engineer to maintain, optimise, and support Linux-based HPC environments powering quantitative research and low-latency trading.

You will manage large-scale HPC clusters, storage, and networking; tune Lustre/GPFS, Slurm/Grid Engine, and RDMA; automate with Ansible or SaltStack; and collaborate with research and trading teams to maximise uptime and performance.