Senior Scientific Platform Specialist (for Linux Research Platform) (ro-900)

Status: 
paused
Location: 
4070 Basel
Start Date: 
2017-09-04
End Date: 
2018-12-31
Deadline: 
2017-08-11 10:00
Hours per day: 
8,00
Hours per week: 
40,00
Workload: 
100%
Total Hours: 
2.960
Assignment: 

Background 

Technical Operations identify specialized technology needs, providing agile and customized infrastructure and services. These deliver “state of the art” computing, enabling our scientists to be innovative, competitive and successful. We provide customized informatics consultancy, tools and services to our scientists. We interface with service providers, internal and external vendors to provide customized scientific leading edge informatics solutions. 
The position will involve architecting, developing and maintaining our scientific computing platforms and working with our scientists on their application needs and translating this to infrastructure needs provided in partnership with our service providers 

Important: Advanced knowledge of Linux system administration, HPC technologies and storage systems, scripting and DevOPS approach to platform administration, scientific application build and tuning are all key requirements. Please check the requirements in detail below. 
 

Tasks & Responsibilities

  • Ensures installation, configuration and operation of the scientific platform environment to achieve the performance and agility of the various applications supported (in the range of several hundreds). 

  • Definition of HPC/HTC workflows and job submission optimization activities 

  • Assist with scientific application and data analysis tool set build, installation, configuration, maintenance and advanced tuning. 

  • Contributes to the concept, planning and execution of projects. 

Requirements: 

We decided to split the must haves in a), b) and c) to make it easier for you to understand the skill set. 

a) TECHNICAL SKILLS

  • At least 7 years of advanced experience working with large scale Linux/HPC environments 
  • Knowledge of HPC cluster build and management tools (e.g bright, xcat); HPC infrastructure components, infiniband networking; Parallel Filesystem (e.g. GPFS, Lustre); GPUs; and monitoring/benchmarking/tuning HPC workloads and applications 
  • Knowledge of Workload management and architecture, queue configuration, such as SLURM, LSF, Gridengine and parallel programming techniques and tuning, openmp, mpi 
  • At least 10 years general Linux system administration skills: DevOPS approach: configuration management (e.g. puppet), automated build/release test & deployment (e.g. jenkins, git); monitoring tools/frameworks (e.g. nagios, ganglia, elk); Scripting: shell, python, perl; 

b) GENERAL SKILLS 

  • Senior level technical operational skills (+7 years), such as troubleshooting, capacity planning, and root cause analysis; writing application and platform documentation; and user training and education experience 
  • Experience in fast changing environments where solutions are deployed and retired at high pace; problem solving attitude; customer orientation and delivery focus with good end user perspective 
  • Good communication and interpersonal skills; advanced English language skill is a must 
  • Clear goal orientation and supportive of change; proactivity, with a clear ability to think beyond boundaries, take controlled risks and assume responsibilities; experience in a global organization, working in an international and multicultural environment is considered a valuable asset 
  • Scientific knowledge or awareness – bioinformatics, cheminformatics, life sciences; desirable understanding of Computer Systems Validation and ITIL concepts; active open source contributor

c) QUALIFICATIONS 

  • Minimum Bachelor computer science or equivalent, ideally Masters. 
  • Professional Linux related certifications, qualifications and industry presentations/recognition.