Staff Platform Engineer - HPC Infrastructure

About the role

CSIT, an agency under the Ministry of Defence (Singapore), is looking for an experienced HPC Staff Engineer to build and run its resilient network infrastructure using cloud-based and software-defined networking technologies such as SD-WAN, ACI and NSX. The engineer leads a team delivering a resilient, scalable and secure HPC platform, covering compute nodes, storage, networks and job scheduling systems, and ensures high availability, scalability and performance.

Key responsibilities

• Lead a team to deliver a resilient, scalable and secure HPC platform, including compute nodes, storage systems, networks and job scheduling systems.
• Design, implement and manage the HPC infrastructure platform to meet organisational needs.
• Design storage solutions for HPC workloads and high-performance networking solutions, including InfiniBand, Ethernet and other interconnects.
• Plan and manage HPC resource capacity, including forecasting, procurement and deployment of new hardware and software.
• Manage HPC clusters, optimising, monitoring and troubleshooting performance, and handling job scheduling and resource allocation.
• Ensure security and compliance, including access controls, security patches and regular security checks.
• Work with data scientists and developers to optimise application performance and provide technical support.

Required profile

• Degree or professional qualification in Computer Science, Computer Engineering or a related field.
• 8+ years of experience managing HPC systems, including Linux, Unix or other operating systems.
• Experience leading engineering teams.
• Nice to have: NVIDIA AI Infrastructure and Operations certification, CKAD, machine learning framework experience, agile and Git.

Required skills

• HPC architectures (clusters, grids, clouds) and job schedulers such as Slurm, Torque and LSF.
• Storage systems (SAN, NAS, object storage) and high-performance networking (InfiniBand, Ethernet).
• Cloud platforms such as AWS, Azure or Google Cloud.
• Scripting (Python, Perl, Bash) and containerisation (Docker, Kubernetes).
• Nice to have: Knative, Run:AI, Grafana, Prometheus, Kyverno, ArgoCD, Rancher, NVIDIA BCM and NVIDIA Superpod.

Only Singapore citizens will be considered. The employer may use AI tools to help review applications, and final hiring decisions are made by humans.