IT specialist in High-Performance Computing for computational core facility
Tomáš Kouba group
IOCB Prague is a world-leading scientific institution dedicated to chemical and biological research. At IOCB, there is a strong emphasis on the translation of results from basic research into applications and commercial assets, such as drug discovery. The IOCB computing core facility is responsible for the purchase, maintenance, and user support of a high-performance computing in-house infrastructure. This infrastructure serves the IOCB research groups in their computationally demanding scientific endeavors task, e.g. image processing, virtual drug-screening, molecular modeling, structural determination, machine learning, and data analysis. The computing core facility provides a periodically upgraded infrastructure currently accounting for nearly 250 computing nodes and 200 TB data storage. The computational core facility has now also partnered with the cryogenic electron microscopy (cryo-EM) facility to provide support for IOCB scientists to analyze large cryo-EM data sets. The infrastructure will be upgraded to meet such demands.
The successful candidate will be a key and valued member of both the computing core and cryo-EM facilities. The post holder will be responsible for the administration and day-to-day user support of the high-performance computing (HPC) infrastructure at the IOCB. The candidate’s main duty will be to ensure smooth running and updating of the hardware infrastructure and its scientific software environment. Priority on the cryo-EM-related activities will be given. The candidate will also be responsible for the technical aspects of the user support, including helping new users to familiarize themselves with the hardware and software environment, bug hunting, and discussing changes in the computing environment to adapt it to the needs of the scientists. The candidate will be in charge of writing and updating documentation of the standard operating procedures for the facilities. Additionally, the candidate will be attending operational meetings; providing statistics and metrics for the running of the computing system; and presenting and reporting on developments.
The candidate will benefit from a stimulating environment with top-tier research scientists, from the access to edge computing hardware, from training and experience on HPC infrastructures, and from the possibility to improve their knowledge in the HPC ecosystem. This all in a flexible and motivating environment in our worldwide recognized research institution.
- Diagnose and fix hardware/software issues
- Warranties executions and communication with vendors
- User support ensuring timely responses to researchers’ queries
- Systems monitoring
- Preparation and updating of system and software documentation
- Preparation tenders for upgrades in infrastructure.
- Maintain scientific software environment with a focus on the cryo-EM software stack
- Adaptation of our HPC environments to better fit the requirements of our scientists
- Proactively improving the codes/scripts run on the systems
- Advanced level Linux (Our current distribution is Centos)
- Advanced level on the installation of software (package managers, compilation from sources, minor patching)
- Expertise/Knowledge in HPC infrastructures including hardware (CPUs, GPUs, interconnects, storage, etc.) and software (Linux, compilers, MPI, HPC tools, parallel file systems, etc.)
- Understanding on parallel computing
- Ability to maintain and support complex research computing systems, ensure service reliability
- Scripting/programming in bash and python programming languages
- Flexible timetable to perform urgent actions out of working hours
- Capacity to communicate and interact with end users
- Fluency in English written and oral
- Experience in scientific computing support
- Experience in high-speed and low latency networking
- Experience in one or more of the following: Parallel file systems/Slurm/Centos/Spack/Ansible/warewulf/Cuda computing/OS remote provisioning/Authentication protocols)
- Experience with infrastructure automation/monitoring tools
- A methodical and accurate approach to work with attention to detail and a willingness to adapt and innovate
- Experience in computer hardware
- Maintenance of PB scale data storage systems
- Fluency in Czech written and oral
- Competitive financial remuneration
- 5 weeks of vacation plus 3 sick days
- Health insurance and full benefits package incl. contribution to supplementary pension insurance and contribution to sports/culture/leisure time
- Meals subsidy
- Financial support for mothers with young children
Full-time employment contract
Fixed-term contract initially for 2 years, with the potential of extension
The position is available immediately
How to apply
For more information please contact, and your application send to, Dr. Hector Martinez-Seara Monne at email@example.com or Dr. Tomas Kouba at firstname.lastname@example.org.
The application should consist of a cover letter (max. two pages) describing your motivation, interests and experience, curriculum vitae, and contact information of at least two references.
The application deadline is 7 January 2022.