IT Administrator - HPC

JOB SUMMARY

The IT Administrator - HPC within the Biomedical Informatics Division is responsible for the installation, configuration, tuning, and troubleshooting of the HPC infrastructure (Linux servers in more than 1 PB environment with over 1000 processing cores) and the associated systems software. He/ She is also responsible for maintaining the integrity and the stability of the HPC.

The administrator provides technical expertise for the use of the HPC systems and applications. He/ she works with users at SIDRA to solve specific computational problems and help researchers to efficiently utilize HPC resources.
KEY ROLE ACCOUNTABILITIES

• Installs software on HPC systems, writes test scripts, troubleshoots application problems and runs benchmarks to evaluate the performance of algorithms on different configurations.

• Assists in monitoring the performance and stability of the HPC resources.

• Oversees the health, compliance and performance of various HPC systems.

• Contributes to the design and configuration of HPC systems in response to the business requirements.

• Leads projects related to the deployment of new systems (hardware and software), the upgrade of existing systems, and the integration among various systems.

• Performs Disk Management and Data Backup.

• Provides monthly reports on the performance and utilization of the HPC systems to their management.

• Installs software & manages file systems, and troubleshoots alerts from monitoring tools.

• Performs programming/scripting to automate some of the operational functions.

• Help researchers evaluate available software and hardware.

• Assist researchers with debugging problems that arise when compiling or using HPC resources or linking to HPC-specific libraries (for example, C, C++, Matlab, Perl, R, openmp, mpi, cuda, pthreads, etc.

• Assists researchers in optimizing or parallelizing existing applications.

• Adheres to Sidra's standards as they appear in the Code of Conduct and Conflict of Interest policies

• Adheres to and promotes Sidra's Values

QUALIFICATIONS, EXPERIENCE AND SKILLS - SELECTION CRITERIA
ESSENTIAL PREFERRED
Education Bachelor's degree in Computer Science, Engineering or a relevant field MS or PhD in computing, engineering or other related field
Experience

• 4+ Years technical systems administration experience; maintaining computer systems infrastructure and its operation, at least 3 of which is in high performance and cluster computing for scientific applications

• Experience in Unix operating systems( Level 2 support or higher)

• Experience in HPC software development and architecture

• Experience virtualization concept and technology

• A good understanding of computer network infrastructure

• Database awareness

• Understanding of traffic classification and prioritization

• Understanding of network security

• Experience building, installing, and configuring a variety of open-source Linux software packages, especially with complex dependencies

• Experience setting up and maintaining a clustered file system such as GPFS or others.

• Experience setting up and maintaining scientific computing clusters and their associated scheduling systems, such as SGE, or PBS

• Previous experience working in Bioinformatics/NGS environment

Certification and Licensure

• Unix / Linux Certified

• VMware/Citrix

• PMP

Job Specific Skills and Abilities

• High level of Technical skills related to systems administration and infrastructure of HPCs

• Extensive experience and skill managing Unix/Linux operating systems in a large-scale system environment

• Shell scripting experience and ability

• Solid understanding of networked computing environment concepts

• Demonstrated ability in managing file systems and storage in an HPC environment

• Experience with batch schedulers (particularly PBS or MOAB)

• Ability to understand the business requirements of the users and translate it into technical requirements

• Ability to manage vendor relationship

• Ability to manage multiple projects simultaneously

• Ability to assess the criticality and urgency of users requirements and prioritize them properly

• Ability to prepare reports on problems root cause or technology evaluation

• Ability to develop and present

• technical information in a format that is understood by non-technical individuals

• Excellent written and interpersonal communications skills and self-motivation are essential.

• Proven ability to work well individually and in a team environment and to produce high-quality work

• Proficiency with Microsoft Office suite

• Fluency in written and spoken English

• C-Programming and porting experience

• Substantial experience with parallel programming environments (MPI, OpenMP, etc.)

• Demonstrated competency with scientific programming languages

• Experience in application profiling and optimization using performance tools on HPC systems

• Knowledgeable about data and security issues relating to clinical information for research.

• Previous experience