Scientific Computing Expert (M/F) – Development and Optimization of an HPC Numerical Code for Space Exploration for the EuroHPC Plasma-PEPSC 2 Project

Job Description

Missions

The Lagrange Laboratory (UMR 7293, CNRS / Université Côte d'Azur / Observatoire de la Côte d'Azur), located in Nice, France, is recruiting a Research Engineer (Ingénieur de Recherche, IR) in scientific computing (ref. E1E45 of the REFERENS framework of the French Ministry of Higher Education and Research) within the framework of the European project Plasma-PEPSC 2 (Community Centre of Excellence for Exascale Plasma Simulations, call HORIZON-JU-EUROHPC-2026-COE-LH-01). The initial appointment is for one year, renewable for a second year.

Plasma-PEPSC 2 is a EuroHPC Centre of Excellence dedicated to the development of exascale applications addressing three grand challenges in plasma physics: (i) magnetic confinement fusion, (ii) laser–plasma interaction, and (iii) space plasmas and space weather.

The successful candidate will join the GIR team (Engineering and Research Group) of the Lagrange Laboratory and will interact closely with the Fluid and Plasma Turbulence team. They will contribute to the development, optimisation and porting of Menura, a hybrid Particle-In-Cell (PIC) code implemented in C++ and parallelised with MPI-CUDA, dedicated to simulating the interaction between the solar wind and Solar System bodies (Earth, planets, comets). The code is already deployed on the Jean-Zay (France) and Leonardo Booster (EuroHPC, Italy) supercomputers, with validated performance (60% strong scaling up to 200 nodes / 800 GPUs; ~100% weak scaling up to 64 nodes / 256 GPUs).

The position is embedded in the Plasma-PEPSC 2 project, which aims to equip Menura and other codes for large-scale simulations on EuroHPC systems on the path towards exascale, in support of ESA space exploration missions. The position will be supervised by Pierre HENRI (CNRS researcher, Deputy Director of the Lagrange Laboratory, local project coordinator) and Dimitri LAVEDER (CNRS Research Engineer, HPC expert, Deputy Technical Director).

Additional information:
- EuroHPC JU website: https://eurohpc-ju.europa.eu/
- Menura code:
◦ GitLab repository: https://gitlab.com/menura_plasma/menura
◦ Reference publication: Behar et al. (2022), Annales Geophysicae (DOI: 10.5194/angeo-40-281-2022).
- CNRS job profile (REFERENS): E1E45 – Scientific Computing Expert: http://referens.esr.gouv.fr/pages/fiche_emploi_type_referens_iii_lir/?refine.referens_id=E1E45

Activity

• Performance characterisation and profiling
◦ Measure and document the performance of Menura on EuroHPC systems (e.g. LUMI, Leonardo) and national clusters.
◦ Identify bottlenecks (algorithms, memory, communication, I/O) using profiling tools (Scalasca, Score-P, Intel VTune, NVIDIA Nsight).
◦ Produce reports to guide optimisation efforts.

• Optimisation and porting to heterogeneous architectures
◦ Implement targeted optimisations (3D domain decomposition, load balancing, cache-friendly data structures, reduction of communication overheads).
◦ Develop and extend accelerator back-ends (porting to Kokkos for CUDA/HIP/SYCL portability).
◦ Benchmark optimised versions and quantify gains in performance and energy efficiency.

• Software engineering and maintenance
◦ Manage the Menura GitLab repository (maintenance, developments, collaborations).
◦ Design and extend regression tests.
◦ Deploy continuous integration (CI) pipelines for automated builds and tests.
Improve modularity, build systems (CMake) and configuration options.
◦ Develop new computational modules.

• Documentation and dissemination
◦ Produce documented releases of Menura (build instructions, user manuals).
◦ Define a contribution model for external groups.
◦ Contribute to the writing of technical reports and project documentation.

Your Profil

Skills

Qualifications and experience
• Degree: PhD, engineering degree, or Master's degree (M2) in scientific computing, plasma physics, or HPC engineering.
• Desired professional experience:
◦ Experience in High Performance Computing (HPC).
◦ Participation in collaborative projects (e.g. EuroHPC CoE, PRACE), or work within a research laboratory (CNRS, CEA, university) or a computing centre (e.g. GENCI, JSC, BSC).

• Required technical skills
◦ Proficiency in modern C++, MPI, and GPU APIs (CUDA, and possibly HIP/SYCL).
Experience with Kokkos, or willingness to learn it rapidly.
◦ Knowledge of performance best practices (vectorisation, cache optimisation, reduction of synchronisation costs).
◦ Use of profiling tools (e.g. Scalasca, Score-P, Intel Advisor, NVIDIA Nsight).
◦ Experience with build systems (CMake) and code management (Git, GitLab CI/CD).
◦ Experience working on supercomputers (EuroHPC, PRACE, GENCI).
◦ Scientific English at C1 level (required for documentation and international collaborations).

• Desirable technical skills (not required)
◦ Experience with PIC or hybrid codes (e.g. iPIC3D, OSIRIS).
◦ Familiarity with the FAIR principles.
◦ Experience in energy optimisation (Green Computing).
◦ French (reading and speaking) is desirable to facilitate integration within the laboratory.


Application Guidelines
• Selection Process:
1. Initial screening based on application materials
2. Technical interview: Hands-on test on a mini HPC project (e.g., optimization of a CUDA or Kokkos kernel, profiling analysis). Questions on parallelization, accelerated architectures, GitLab, and EuroHPC supercomputers.
3. Final interview with the local Plasma-PEPSC 2 recruitment committee.

Required Documents
• Detailed resume (including links to open-source contributions (GitHub/GitLab) and contact information for two letters of recommendation (academic or professional))
• Cover letter in English (1–2 pages) including: Experience in HPC computing, parallelization, HPC profiling, GitLab, accelerated architectures, and interest in plasma simulations and the Plasma-PEPSC 2 project.

Your Work Environment

The J.-L. Lagrange Laboratory (https://lagrange.oca.eu/) is a Joint Research Unit (UMR) of the Observatoire de la Côte d'Azur, the CNRS and Université Côte d'Azur. It is a multidisciplinary laboratory bringing together teams in astrophysics (planetary science, stellar and solar physics, galaxies and cosmology), fluid mechanics, signal and image processing, and instrumentation for astronomical observation at high spatial resolution and high dynamic range. Cross-cutting expertise in high performance computing lies at the heart of the teams' ability to develop new theories and models and to confront them with observations acquired on major ground-based and space telescopes.

Constraints and risks

-

Compensation and benefits

Compensation

Gross monthly salary range (based on experience): between €3,175.08 and €3,681.87

Annual leave and RTT

44 jours

Remote Working practice and compensation

Pratique et indemnisation du TT

Transport

Prise en charge à 75% du coût et forfait mobilité durable jusqu’à 300€

About the offer

About the CNRS

The CNRS is a major player in fundamental research on a global scale. The CNRS is the only French organization active in all scientific fields. Its unique position as a multi-specialist allows it to bring together different disciplines to address the most important challenges of the contemporary world, in connection with the actors of change.

CNRS

The research professions