RESPONSIBILITIES

• Day-to -day operational maintenance, support, and upgrades for a 2000+ core high performance compute cluster
• Monitoring cluster performance, job submissions, file system usage, and user activity
• Installing open-source and vendor supported bioinformatics applications on our clients HPC cluster and working with researchers to develop submission scripts
• Diagnosis and resolving operational issues quickly and effectively
• Updating documentation for application usage on a dynamic support portal, and generate usage reports
• Working closely with other team members to implement innovative and complex solutions, ensuring that upgrades and changes comply with established guidelines and processes
• The successful candidate will apply HPC and Linux expertise to collaborate with stakeholders across IT and domain disciplines to expand HPC use in support of world class, cutting-edge scientific research.

REQUIREMENTS

• Bachelors and 3+ years of experience with Linux/Unix variants, especially RedHat/RHEL and its derivatives
• 3+ years of experience supporting high performance clusters with Grid Engine experience (in any variant)
• Hands-on experience supporting IBM Spectrum Scale (formerly GPFS) or equivalent experience with other distributed file systems such as Lustre, PVFS, GFS, etc.
• Demonstrated working knowledge of popular bioinformatics applications and ability to compile, package, install, and upgrade software as well as assist researchers with job submission scripts. (Experience using Module Environments and EasyBuild preferred.)
• Scripting experience (Perl, Python, Ruby, R, bash, etc)

• Excellent written and verbal communication skills. Ability to create concise documentation for application usage
• Able to clearly present ideas to both technical and non-technical users in formal and informal settings

PREFERENCES

• Automation/configuration management experience (Chef, Puppet, Ansible, Salt, etc.)
• Experience running parallel jobs with OpenMP or MPI Libraries
• Knowledge of GPU computation and CUDA
• Experience configuring and running BrightCluster Management Software

TERMS

LOCALE

COMPENSATION

HOW TO APPLY

DEADLINE

POLICY