Hpc Administrator Gauteng - South Africa
University of Pretoria
DEPARTMENT OF INFORMATION TECHNOLOGY SERVICES HIGH-PERFORMANCE COMPUTER (HPC) SYSTEM ADMINISTRATOR PEROMNES POST LEVEL 7 The successful candidate's responsibilities will include, but are not limited to: Operating system installation and maintenance: Install, configure, and maintain operating systems (e.g., Linux) on the HPC cluster nodes; Apply patches, updates, and security fixes to ensure the stability and security of the system; Troubleshoot and resolve operating system-related issues; Cluster management, system installation and maintenance: Deploy, configure, and manage cluster management software (e.g., Slurm, PBS Pro) to allocate computing resources efficiently; Monitor system performance and optimise cluster utilisation; Implement and maintain job scheduling policies to meet the diverse needs of researchers; Cluster internal network management: Configure and manage internal network infrastructure for optimal performance and reliability; Troubleshoot network connectivity issues, and implement solutions as necessary; Ensure effective communication between cluster nodes and storage systems; Cluster storage management: Administer storage solutions (e.g., Lustre, BeeGFS) for high-performance data access and storage; Allocate and manage storage resources according to research requirements; Implement backup and disaster recovery strategies to safeguard research data; User management: Provide user support and assistance in accessing and utilising HPC resources; Manage user accounts, permissions, and quotas; Offer guidance on best practices for efficient utilisation of HPC resources; Documentation development and training: Develop and maintain comprehensive documentation for HPC system configuration, usage, and troubleshooting procedures; Conduct training sessions and workshops to educate researchers on HPC best practices and utilisation techniques; Liaison with stakeholders: Collaborate with faculty members, researchers, and other stakeholders to understand their computational needs and requirements; Communicate technical information to both technical and non-technical audiences; Act as a liaison between research teams and the IT department to address infrastructure-related issues; Application support: Assist researchers in installing, configuring, and optimising scientific applications and tools on the HPC cluster; Troubleshoot application performance issues and recommend optimisations; Stay updated on emerging technologies and trends in HPC and scientific computing. Closing date: 04 JUNE 2024 No application will be considered after the closing date, or if it does not comply with at least the minimum requirements MINIMUM REQUIREMENTS: Relevant Bachelors/BTech degree; with A total of four years' experience in: Administering and managing HPC clusters in a research or academic environment; Linux system administration and shell scripting. Cluster management systems (e.g. Slurm, PBS Pro) and parallel file systems (e.g., Lustre, BeeGFS); OR Relevant three years National Diploma; with A total of six years' experience in: Administering and managing HPC clusters in a research or academic environment. Linux system administration and shell scripting. Cluster management systems (e.g. Slurm, PBS Pro) and parallel file systems (e.g., Lustre, BeeGFS). REQUIRED COMPETENCIES (SKILLS, KNOWLEDGE AND BEHAVIOURAL ATTRIBUTES): Knowledge of: Linux operating structure architecture; Cluster computing concepts; High-performance storage; Advanced storage design; Understanding of networking concepts and protocols; Technical competencies: Linux system administration and shell scripting; Cluster computing management; Network administration; High-performance storage management; Behavioural competencies: Problem-solving skills, calm in a crisis, good communication skills with users and managers, logical, meticulous, good judgement skills; Ability to work independently and collaboratively in a dynamic research environment; Ability to perform fault-finding and implement solutions. ADDED ADVANTAGES AND PREFERENCES: Relevant post-graduate qualification; Two years' experience with: Network design; IT Infrastructural library (ITIL) and change control; User-directed documentation development and training; Certification as a: Linux server administrator; Server administrator; Network administrator; Cluster administrator. The annual remuneration package will be commensurate with the incumbent's level of appointment, as determined by UP policy guidelines. UP subscribes to the BESTMED and UMVUZO medical aid schemes and contributes 50% of the applicable monthly premium.
Apply Now
Facebook
WhatsappRelated Jobs
ERP/IT Administrator - Boksburg
...
Servicenow Engineer Cape Town - Cape Town Region
Sabenza IT Recruitment
...
Erp Administrator Boksburg, South Africa - Boksburg
Southey Contracting Offshore Division
...
Junior System Administrator Durban - Durban
Jeys Recruitment
...
It Administrator Benoni - Benoni
Peoplefinder Career Placements
...