HPC Systems Engineer

Job Description

Job Description

Corvid Technologies is seeking HPC Systems Engineers with a strong background and enthusiasm for Linux to support our Linux-based High Performance Computer consisting of 80,000+ processor cores. If you enjoy learning, playing with hardware, optimizing performance, efficiency, and spend most of your time on the command line, this is the job for you.

Candidates will be responsible for the following:

• Supporting software installation and configuration of license management servers (e.g., FlexLM or RLM)
• Implement site-to-site VPNs (e.g., IPSEC tunnels) to customers on customer HPC clusters
• Troubleshoot slow, hanging, or failing HPC jobs on internal or customer HPC clusters
• Automate repetitive tasks and implement custom solutions using scripting/programming languages such as Bash or Python
• Provide guidance and support on HPC best practices and solutions for internal and external customers
• Troubleshoot hardware and software issues on Linux servers
• Installation of new hardware into existing compute clusters
• Design, test, and implement an HPC environment consisting of a provisioner (e.g. xcat, warewulf), scheduler (e.g. Slurm, SGE, PBS), RDMA connections (e.g InfiniBand), a subnet manager, and 5+ compute nodes within the first 180 days of employment
• Obtaining a CompTIA Security+ certification within the first year of employment

Requirements :

• Bachelor's degree in Engineering or related STEM field (master's preferred)
• Scripting experience
• Professional/personal experience using command-line Linux (RHEL derivatives preferred)
• Experience in one or more engineering computational code OR 2+ years of IT-related experience (e.g., user support, basic networking, Linux server administration, a home Linux environment)
• Obtain and maintain a U.S. security clearance

Preferred Skills:

• Past experience as an HPC user on a large-scale cluster
• Past experience managing information systems within a classified environment
• Experience installing, configuring, and maintaining job management tools (such as SLURM, Moab, TORQUE, PBS, etc.)
• Experience configuring, installing, and troubleshooting MPI and OpenMP applications
• Experience with operating system deployment tools (e.g. XCAT, ROCKS)
• Hands-on experience of at least one distributed file system (Spectrum Scale-GPFS, Lustre, BeeGFS, Gluster, IMRIX, PVFS, etc.)
• Direct experience working with InfiniBand
• Experience configuring, installing, tuning, and maintaining scientific software on large-scale systems
• Experience supporting HPC compilers and libraries
• Experience with configuration management tools such as Ansible or Puppet
• Familiarity with authentication and access control systems (ADFS, LDAP, Kerberos)
• Active U.S. security clearance
• Current and active CompTIA Security+ certification

Why Corvid?

Founded in 2004, we are a group of over 300 engineers and scientists, about three-quarters of whom hold master's degrees or PhDs, that provide end-to-end solutions, including concept development, design and optimization, prototype build, test, and manufacture. We leverage the predictive capabilities of our high-fidelity computational physics solvers, indigenous massively parallel supercomputer system, prototyping plant, and ballistics and mechanics lab to investigate a variety of high-rate physics phenomena.

The results are complex engineering solutions for a range of applications: aircraft, ballistic missile defense, cybersecurity, motorsports, armor development, biological systems, and missile and warhead design and development. These results are achieved with optimal design and cost efficiency due to the predictive capability of Corvid's tools and our in-house, end-to-end integrated approach, which differentiates Corvid from the market.

We value our people and offer employees a broad range of benefits. Benefits for full-time employees include:

• Paid gym membership
• Flexible schedules
• Blue Cross Blue Shield insurance including Medical, Dental, and Vision
• 401(k) match up to 6%
• Three weeks starting PTO; increasing with tenure
• Continued education and training opportunities
• Uncapped incentive opportunities

#IND1