[ad_1]

For our international client in Rijswijk (ZH) we are looking for a High Performance Computing Engineer.

Location: Rijswijk
Start: 2-10-2017
End: 1-10-2019
40 hrs./week

The HPC R&D Engineer role is focused on meeting the infrastructure development and support requirements unique to Research and Development activities. Responsibilities include developing and deploying pre-production operating system images and utilities, deploying and supporting novel hardware solutions and working closely with R&D staff to ensure that their specific HPC infrastructure requirements are met.

Accountabilities:
The configuration, design, enhancement, testing, integration, implementation and documentation of hardware, operating systems and utilities
– 2nd and 3rd line support of hardware, operating systems and utilities
– Coordinating the work of team members from R&D Engineering, Production Engineering and Operations in the delivery of products and services to the R&D community
– Working directly with R&D staff developing, deploying and supporting infrastructure unique to Research requirements
– Providing ad hoc HPC consultancy to R&D staff
– Operating system and utility tuning in collaboration with R&D staff
– Managing projects to deploy infrastructure in support of R&D projects

Skills & Requirements:
– Solid experience in designing and deploying HPC infrastructure
– Strong customer focus and interpersonal skills
– Experience with HPC workflows associated with two or more of Seismic Signal Processing, Reservoir Modelling, Basin Modelling, or Thermodynamic Modelling
– Strong experience working with the Linux operating system as an engineer and systems administrator.
Experience with senior level administration – kernel tuning, monitoring packages such as Nagios and Gangalia
– General scripting abilities with such languages as Perl, Python
– Experience with RedHat Satellite Server from both a user and developer perspective.
– Knowledge of running and debugging MPI applications
– In-depth experience with design and implementation of multiple job scheduling tools including LSF

Position Requirements:
– Experience with cluster and parallel file system administration such
(E.g. Lustre, Intel Lustre, ext4)
– Strong knowledge of HPC software stack, libraries and compilers (e.g. Intel compiler suite/toolkit, OpenMPI, MVAPICH, MPSS)
– Knowledge of cloud computing design and operation
– Strong understanding of Information Risk Management applied in an HPC environment
– Knowledge of a variety of components typically used in HPC infrastructure, including Intel/AMD commodity servers, Ethernet and Infiniband interconnects, fibre channel networks
– Knowledge of novel technologies/tools such as GPUs, Xeon Phi, Cuda, Docker,
– Knowledge of Cloud technologies (IE AWS, Azure, Google Cloud)
– Good planning, organization and project management skills
– Comfortable with virtual working in a global environment as the norm

Special Challenges:
– The ability to deliver effective services in an environment that at times will be relatively unstructured in order to meet the needs of R&D staff
– Effectively working with somewhat overlapping scope between Production Engineering and R&D Engineering
– Focusing on activities that are a value add to R&D while relying on Production Engineering and Operations staff to handle the more structured aspects of infrastructure development and support
– Possessing/developing deep technical skills in several very specialized areas (Linux, High Performance Desktops, High Performance File Systems, Storage Area Networks, Cluster Computing, High Speed Cluster Interconnects, Desktop Virtualization, HPC Job Scheduling, Novel technologies such as GPGPU and FPGA…)
– The ability to work in a very fast paced and somewhat unstructured environment
– Planning, organizing, managing and delivering projects in a shared resource

Interested? Please send us your English CV, motivation and hourly rate.

[ad_2]

Source link