Distinguished HPC Engineer
United States6d ago
Key details
- Location
- United States
- Work style
- Onsite
- Level
- Lead / Staff+
- Job type
- Full-time
- Function
- Software engineering
- Focus area
- Infrastructure / Cloud
- Posted
- 6d ago
Skills
About the role
Primary Responsibilities:
• Design and implement high-performance computing clusters to ensure they meet the required
performance, scalability, reliability and availability standards.
• Provide subject matter expertise in HPC storage, file systems and Linux to DST clients and
internal teams.
• Deploy and maintain cluster management software such as Bright Cluster Manager to
streamline administration and operations.
• Set up, configure, and troubleshoot HPC job schedulers like SLURM, LSF, or UGE to optimize
job scheduling and resource allocation.
• Install, configure and maintain containers, container applications and orchestration tools.
• Deploy and manage advanced health monitoring systems to ensure the HPC infrastructure is
operating efficiently and to preemptively identify issues.
• Automate software installations and system configurations using Ansible to ensure consistency
and efficiency across deployments.
• Stay up to date with the latest developments in HPC technologies and research new solutions to
improve system performance and capabilities.
• Provide Jira support to maintain and improve DST’s project and ticket management.
• Maintain clear and effective communication with clients, management, and internal teams to
ensure project goals and expectations are met.
Requirements:
• Extensive experience with Linux operating systems, including system configuration,
troubleshooting, and performance tuning.
• Advanced expertise with parallel storage systems, InfiniBand, and Ethernet networking to
ensure high-performance data transfer and storage solutions.
• Proven expertise in designing and building HPC clusters from the ground up, including
hardware and software integration.
• Advanced knowledge and hands-on experience with Bright Cluster Manager, Slurm for job
scheduling, and Ansible for automation.
• Intermediate knowledge of GPUs and associated hardware/software, including configuration,
optimization, and debugging.
• Intermediate Jira skills
• Strong organizational skills to manage multiple projects efficiently and excellent
communication skills to interact effectively with various stakeholders
How well do you match this job?
Free account needed to apply or save. It takes a minute, and we'll bring you right back to this job.