The Berlin Institute of Health (BIH) is a joint venture of the Charite University Medicine and the Max Delbrueck Center for Molecular Medicine (MDC) for interdisciplinary translational system medicine.
We are looking for a highly motivated, solution-oriented individual to join us as team leader HPC systems. You will be responsible for the BIH high-performance compute cluster, connected servers and systems, and corresponding networking. In this position, you will drive the course of change and improvement while retaining stability of our systems. The position works in close collaboration with MDC central-IT, core unit bioinformatics, and several research groups that provide and/or operate substantial scientific computer hardware themselves.
Working in the BIH gives you the opportunity to support excellent scientific facilities in their interesting projects with the aim of translational biomedical research and bringing research results closer to the patient for diagnostics or treatment.
- Lead and organize the operation and expansion of the BIH scientific compute infrastructure that supports a wide range of user groups and needs including genome analysis, machine learning and simulations
- Administration, monitoring, tuning and extension of Linux-based HPC cluster, and connected systems, such as job queue and high performance storage systems, identify and realize synergies with compute resources of individual research groups
- Lead a team of system engineers and administrators
- Perform root-cause analysis and fixing of errors and performance problems; monitor, adjust, and tune the queuing system
- Work with MDC central IT on topics such as networking and backup&archiving, realize seamless data flow from sequencing and mass spec devices, cooperate with core unit bioinformatics on omics data management
- Organize and deliver user support; create and update documentation; educate users in HPC usage
- Contribute to IT security concepts and policies and perform corresponding technical implementations; contribute to data privacy concepts and policies and to the implementation of the corresponding processes
- Contribute to the evaluation of new technologies and resource planning including usage of tier 1/tier 2 clusters at partner institutions or commercial cloud providers; define future hardware and software purchases in cooperation with the HPC steering committee
- MS degree in Computer Science or similar demonstrable skills required; 3+ years experience in HPC system administration required; project or team leader experience is expected
- In-depth understanding of scientific computing and large scale data management needed; a relevant PhD and/or experience in biomedical environment are a plus
- Excellent demonstrable system and HPC administration skills required: ZFS, NFS, GPFS, GridEngine, Kerberos, AD/LDAP, monitoring, automation, and testing systems
- Experience with Puppet/Ansible/Salt/Chef, Docker/Rocket, iRODS, SLURM/TORQUE, CentOS, OpenLDAP, Ganglia/CheckMK, PostgreSQL, virtualization technologies, OpenStack and good programming skills are a strong plus
- Proven ability to create well-structured configuration and deployment systems, and to write technical and user-targeted documentation required
- Team-oriented with excellent communication skills in English; good knowledge of German is a plus
The MDC is an equal opportunity employer and supports gender equality.
Please send your applications by 2018-08-19 preferably as one PDF file to firstname.lastname@example.org
Salaries are set according to qualification and experience based on regulation of TVöD Bund starting at E14 with additional company pension scheme (VBL) and negotiable extra pay.
As soon as possible
Appointments are made for an initial period of 2 years with the option to become permanent afterwards.
Dieter Beule email@example.com