HPC System Administrator / Scientist

IDEADED; Cataluña; Presencial; EUR 55.000 - 75.000; Jornada completa

Descripción de la vacante

IDEADED in Viladecans, Spain, seeks a full-time HPC System Administrator / Scientist to install, configure, and optimize our HPC clusters and software stacks.

You will document configurations, assist scientists, manage storage and networks, and contribute to capacity planning and tool evaluations.

Formación

• Bachelor-level degree or equivalent practical experience in a related technical field.
• Expert-level Linux with scripting in Bash and Python.
• 3–5 years hands-on HPC experience; strong problem-solving under pressure.

Responsabilidades

• Install, configure, maintain, and optimize IDEADED HPC clusters and software stacks.
• Support scientists and engineers by optimizing codes and resources.
• Document configurations, procedures, and incident reports for continuity.

Conocimientos

Linux proficiency

Bash scripting

Python scripting

HPC experience

Fortran

C/C++

Slurm

Spack/EasyBuild

MPI (OpenMPI/Intel)

Environment modules

Performance profiling

Educación

Degree in CS/Engineering/Physics

Herramientas

OpenMPI

Intel MPI

CUDA

Spack

EasyBuild

Lmod

Descripción del empleo

Company Description

IDEADED is a Spanish deep-tech company with over 10 years of experience developing next-generation semiconductor technologies. We combine advanced research, design innovation, and process engineering to create solutions that go beyond traditional silicon and support Europe’s technological sovereignty.

Driven by scientific excellence and industrial impact, IDEADED is building a more sustainable and competitive microelectronics ecosystem.

Role Description

This is a full-time, on-site role based in Viladecans for an HPC System Administrator / Scientist. The role involves installation, configuration, maintenance and optimization of the IDEADED HPC clusters and associated software stacks, while ensuring stability, security, and performance. This position requires a strong technical foundation and the ability to support the growing team of scientists and engineers by managing, monitoring, and optimizing high-performance computing (HPC) infrastructure, including servers, storage, and networks. It also includes documenting system configurations, operational procedures, and incident reports to ensure continuity and knowledge sharing, contributing to capacity planning, and evaluating new tools and architectures to support IDEADED’s advanced technologies.

Qualifications

• Relevant degree in Computer Science, Engineering, Physics, or a related technical field, or equivalent practical experience.
• Expert-level proficiency with Linux operating systems, including deep command-line fluency and advanced scripting capabilities in Bash and Python.
• Minimum 3–5 years of hands-on experience in HPC environments.
• Demonstrated strong proficiency in Fortran and C/C++ to support users with modern coding practices, library versioning (e.g., BLAS, LAPACK, FFTW, Intel MKL), and to assist in debugging and optimizing user applications.
• Experience managing and configuring the Slurm workload manager, including queue management, user policy enforcement, and troubleshooting job failures.
• Proficient in compiling packages using Spack or Easybuild, including MPI libraries (e.g., OpenMPI, Intel MPI) and GPU toolkits (e.g., CUDA).
• Experience implementing and maintaining environment modules (e.g., Lmod/Environment Modules) is required.
• Experience installing and configuring user-facing performance profiling tools to support code optimization efforts is required.
• Experience compiling, optimizing and executing performance-tune of scientific application hands-on experience in Density Functional Theory (DFT) codes (e.g., FHi-aims, Quantum ESPRESSO, Siesta) and Molecular Dynamics (MD) codes (e.g., LAMMPS), tailoring builds for specifichardware architectures.
• Experience deploying and maintaining monitoring stacks to track real-time health of all cluster components.
• Demonstrated strong problem-solving skills and the ability to remain composed and effective under pressure during critical incidents.
• Ability to work collaboratively with multidisciplinary scientific teams and communicate complex technical topics clearly.