Colorado Technology Jobs

Colorado Jobs

Job Information

University Corp. For Atmospheric Research (UCAR) HPC Systems Engineer III in Boulder, Colorado

Application Deadline: This position will be posted until September 25, 2020.Relocation: Partial relocation assistance is available for this position.Work Authorization: UCAR/NCAR will not sponsor a work visa to fill thisposition.Where You Will Work:NCAR's Computational and Information Systems Laboratory (CISL) is aleader in supercomputing and data services necessary for the advancement ofatmospheric and geospace science. CISL's mission is to remain a leader atthe forefront of ensuring that research universities, NCAR, and the largeratmospheric, oceanographic, and related research communities have accessto the computational resources they need for their research. To fulfill theneed for a stronger workforce at the intersection of High PerformanceComputing (HPC) and geoscience problems, CISL engages in education andoutreach activities to inspire and attract a diverse future workforce.Primary job location is in Boulder Colorado. Production systems supported arelocated at the NCAR Wyoming Supercomputing Center (NWSC) located inCheyenne Wyoming. May be required to work at the NWSC during periods of systeminstallation, system upgrade, or system troubleshooting.What You Will Do:The High Performance Computer (HPC) Systems Engineer III providesleadership and support for the Computational .and. Information SystemsLaboratory's (CISL) high-performance supercomputers, storagesystems, data archival systems, high-performance networks, and datatransfer services. The environment is composed of multi-vendor resources withnumerous specialized hardware components and requires coordination andcommunication with the other groups and divisions within CISL.The position is primarily responsible for leading the design,installation, integration, configuration, maintenance,administration, troubleshooting, and operation of both software andhardware systems, including peta-scale computational systems, peta-scalestorage systems, data archival systems, object storage systems, datatransfer services, scheduling environments, and high-speed networks.Responsibilities:Software Engineering and DevelopmentDevelops, implements, and documents new features or capabilities in systemadministration, system and security monitoring software, and systemanalytics software.Develops and maintains systems software as necessary for the deployment andmanagement of all aspects of high-performance supercomputers, clusters,storage, and network fabrics.Performs installation and necessary hardware and software integration as partof the HPC infrastructure deployments and upgrades.Leads software development projects including requirements gathering,design, and project management. Helps define group standards and guidelinesfor software development and documentation.Writes code to enhance system management capabilities of the HPCinfrastructure and automate repeatedly performed system administration tasks.Manages, designs, and develops benchmarking tool suites for use duringprocurements and for ongoing performance monitoring of the high-performancecomputing environment. Develops acceptance testing criteria and applicationsfor system procurements.Research and EvaluationResearches new and emerging technology (e.g., cloud), evaluates thepotential impact of the new hardware and software technology on workflows andplans, and makes recommendations to the HPCD division and CISL managementfor future procurement of hardware and software products, configurations,and functional enhancements or upgrades in support of the high-performancecomputing environment.Performs evaluations and benchmarks, and compiles reports on new hardwareand software systems related to the high-performance computing environment(i.e., computing, storage, networking).Participates in projects relating to the high-performance computingenvironment and may have direct responsibility for design and procurementrecommendations. This may also include development of systems level code tosupport the various aspects of the HPC infrastruct