Senior HPC Systems Administrator

RedLine; Berkeley (CA); Remote; USD 140,000 - 190,000; Full time

Benefits offered by this job

Paid time off

401k match

Health care benefits

Job summary

RedLine is seeking a Senior High Performance Computing (HPC) Administrator to support on-premise HPC environments and a flagship supercomputer project at Lawrence Berkeley National Laboratory. The role requires strong Linux, security, configuration management, and networking expertise, with leadership responsibilities and 24x7 on-call support.

US citizenship and the ability to obtain a Public Trust clearance are required.

Qualifications

• 10+ years in Linux admin in large, production HPC environments.
• Demonstrated leadership for technical solutions and admin teams.
• Experience with batch systems, storage, networking and backup systems.
• Ability to work independently and manage multiple projects.

Responsibilities

• Lead a team to administer resources from OS to service nodes in on-prem HPC environments.
• Install software on compute resources, service nodes and parallel filesystems.
• Develop/implement system monitoring, benchmarking and documentation.
• Evaluate performance impacts of OS changes and policy updates.
• Lead resource optimization and job scheduling policies.
• Provide 24x7 on-call support and researcher assistance.
• Provide technical leadership and direction for team members.
• Manage change requests and communicate with customer management.
• Travel to CA client site ~1 week per quarter.

Skills

Linux administration

Leadership

HPC networking

Scripting/Automation

Batch systems (SLURM)

Lustre storage

InfiniBand networking

Configuration management (Ansible)

Communication

Tools

SLURM

Lustre

Ansible

InfiniBand

Job description

and promotes a high level of staff retention. We offer services ranging from full life cycle HPC systems engineering to remote managed services to HPC program analysis.

RedLine is looking for a Senior High Performance Computing (HPC) Administrator to join our team. This position will work on various on-premise installations in support of new flagship supercomputer and managed infrastructure located at Lawrence Berkeley National Laboratory. The ideal candidate will be an experienced individual with a strong security, Linux, HPC, configuration management, systems automation and networking background. This position supports requires strong organization, management and customer facing skills.

The customer supports a high-visibility, next-generation national computing initiative supporting cutting-edge scientific research and discovery. As a Sr. HPC System Administrator, you will directly contribute to the reliability, performance, and availability of the advanced computing environment that enables large-scale scientific research and breakthroughs with far-reaching impact.

US citizenship and the ability to obtain a Public Trust clearance is a requirement to apply. This is a remote position but will work Pacific Time core hours. This full-time position offers a full benefits package including paid time off, 401k match, and health care benefits.

Job Responsibilities:

Lead a team to administer resources from the operating system and above within on-premise HPC environments. Efforts include, but are not limited to:

• Integration and configuration of compute resources and service nodes
• All software installations on compute resources, services nodes, and parallel filesystems
• Develop/implement system and performance monitoring and benchmarking
• Maintain system documentation
• Evaluate performance impacts of planned operating system changes
• Lead resource optimization and job scheduling software and policies
• Provide technical support to researchers using HPC resources, troubleshoot problems and develop appropriate computational strategies
• Provide emergency support on a 24x7 basis.
• Provide technical leadership and direction for other team members. Maintain team focus on production uptime and model performance.
• Review and present all change management requests to customer management.
• Work both independently and as part of the team; able to concurrently work on several projects.
• Effectively communicate with people of diverse backgrounds and computer knowledge.
• Manage individual and team task pipelines, ensuring all deliverables are met and tracking systems are consistently updated.
• Solicit and analyze customer feedback, ensuring critical issues are effectively communicated to the team and captured as trackable deliverables.
• Manage individual and team task pipelines, ensuring all deliverables are met and tracking systems are consistently updated.
• Solicit and analyze customer feedback, ensuring critical issues are effectively communicated to the team and captured as trackable deliverables.
• Travel to the client site in California approximately 1 week per quarter with some additional travel upon installation of the system.

Requirements:

• Minimum of 10 years RedHat, Rocky, and/or CentOS Linux system administrator experience.
• Technical leadership experience in a large, production environment – leadership for the technical solution and the system administration team.
• Demonstrated ability to configure, deploy and manage major system areas such as batch system, network, data storage, backup system, database system, or distributed computing
• Experience with configuration management tools (e.g., Ansible)
• Ability to work both independently and as part of the team; flexibility in dealing with assignments and in working on several projects simultaneously
• Ability to effectively communicate with people of diverse backgrounds and computer knowledge.

Preferred Skills:

• HPC system administration experience is highly preferred.
• Experience with batch systems (e.g., SLURM)
• Experience managing parallel and cluster file systems (e.g., Lustre)
• Network management experience, including in an HPC context (e.g., InfiniBand)