High Performance Systems Engineer - Hiring in process/Finished, not possible to apply

Description of the position
Experiments located at the MAX IV laboratory collect and process large amounts of data for scientific analysis.

For this purpose, MAX IV operates state-of-the art computational infrastructure, including HPC cluster resources, a Data Acquisition (DAQ) cluster and a high performance storage cluster, interconnected through an infiniband fabric. Detectors at the experiments are connected to the compute infrastructure through high speed ethernet network (10/40/100GE).

Ingest and processing of data from high rate detectors require all components of the computing infrastructure to be well tuned for performance, and 24/7 operation of the MAX IV facility requires high availability of the computational resources. At the same time, new generations of detectors and new analysis pipelines are bringing new challenges in compute and storage system performance requirements, necessitating a continuous evolution of the systems.

We are looking for a skilled and highly motivated new colleague to join our IT infrastructure team to work with us on the high performance aspects of our infrastructure.

Work duties and areas of responsibility
The successful candidate will have the possibility to engage in a broad spectrum of aspects in high-end computing related to data processing at MAX IV, including HPC, DAQ, and high performance storage and networking.

He or she will contribute on daily basis to the reliable operation of MAX IV’s compute infrastructure, and participate in its evolving design.

This includes evaluation of new technologies and architectures for suitability and increased performance as required by upcoming data producers and analysis pipelines.

The position will naturally lead to participation in  in collaborative projects within MAX IV, other Lund University units and national and international computing infrastructures.

The successful candidate is expected to actively contribute to the future development, and be able to follow and analyse the trends and new developments in compute, storage and networking technologies.

Requirements
- Experience with operating high performance compute systems
- Solid understanding of the Linux operating system
- Good scripting skills
- Excellent communication and teamwork skills
- Fluent in English

Desirable
Experience with one of more of
- server performance tuning
- high performance networking
- GPFS/Spectrum Scale
- Infiniband fabrics
- managing job queueing systems (e.g. slurm)
- container technology (docker, singularity) and container orchestration (kubernetes)

The successful candidate is creative, service minded, takes initiative, has a problem solving analytical ability and the ability to cooperate.