Researcher in High Performance Calculation (Exascale) M/F

CNRS; France; On-site; EUR 45,000 - 60,000; Full time

Job summary

CNRS at the Maison de la Simulation on the Paris-Saclay campus in Essonne seeks highly motivated researchers to advance exascale computing. You hold a PhD in computer science with experience in scientific computing and are proficient in Python, C/C++, or Fortran, with strong parallel programming knowledge.

You'll work in an agile team to develop scalable patterns, proxy apps, and development kits for the scientific community.

Qualifications

• PhD in computer science or a related field with experience in scientific computing.
• Strong programming skills in Python, C/C++, or Fortran and parallel programming (GPU, multi‑threading).
• Experience with Git, GitHub, CMake, Docker, Spack, GTest, CTest and collaborative development.
• Excellent written and oral communication in French and English.

Responsibilities

• Explore selected algorithmic patterns including PDE discretization and adaptive mesh refinement.
• Collaborate with the application community to define representative proxy applications.
• Develop scalable technical solutions using NumPEx libraries and tools.
• Optimize performance and portability with parallel programming models and abstractions.
• Create benchmarks and metrics to assess performance, scalability, and portability.
• Integrate and deliver development kits for the application community.
• Support knowledge transfer through training and documentation.
• Contribute to Agile processes by planning, monitoring, and coordinating with teams.

Skills

Python

C/C++

Fortran

Parallel programming

Git

GitHub

CMake

Docker

Spack

GTest

CTest

Agile

Education

PhD in computer science or related field

Tools

Git

GitHub

CMake

Docker

Spack

GTest

CTest

Job description

Organisation/Company CNRS Department Maison de la Simulation Research Field Computer science Mathematics » Algorithms Researcher Profile First Stage Researcher (R1) Application Deadline 28 Oct 2026 - 23:59 (UTC) Country France Type of Contract Temporary Job Status Full-time Hours Per Week 35 Offer Starting Date 4 Jan 2027 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

Launched in 2023 for a six-year period, the NumPEx PEPR (“High-Performance Computing for Exascale”) contributes to the design and development of the numerical methods and software components that will equip future European exascale and post-exascale machines. The program is funded by the French government and led by CNRS, CEA, and Inria.

NumPEx also aims to support the scientific and industrial communities in fully exploiting the capabilities and potential of these new architectures. Application domains include, among others: weather forecasting, climate science, aeronautics, automotive, astrophysics, high-energy physics, materials science, energy production and management, biology, and healthcare.

The Exa-DI project, one of the five NumPEx projects, aims to accelerate the development of exascale applications by providing “development kits” based on the NumPEx software stack. These kits can be easily deployed and instantiated in different contexts, providing sustainable, high-performance, and portable solutions to the algorithmic and communication patterns most commonly encountered in exascale applications. These patterns will be addressed iteratively through an agile co-design and co-development process with the application community.

Exa-DI is looking for highly motivated researchers with a strong background in scientific computing to explore the scalability of different algorithmic patterns in an agile development environment.

Within an Agile team that is currently being established:

• Based on your expertise, you will contribute to the exploration of selected patterns, including the discretization of partial differential equations, block-structured adaptive mesh refinement, particle methods, and more.
• You will collaborate with the application community to identify and specify “proxy applications” that are representative of the main technical challenges associated with each pattern.
• You will develop technical solutions to scale these proxy applications, leveraging the libraries, frameworks, and tools developed by the other NumPEx teams.
• You will optimize performance and portability through informed use of parallel programming models and abstraction layers.
• You will develop benchmarks and metrics to assess the performance, scalability, and portability of the proposed solutions.
• You will integrate and deliver “development kits” for the application community.
• You will facilitate knowledge transfer by providing support and training.
• You will actively contribute to the Agile approach by helping improve processes, plan and monitor the team's work, conduct progress reviews and demonstrations, and coordinate with other teams.

The positions are based at the Maison de la Simulation, on the Paris‑Saclay campus in Essonne. The Maison de la Simulation is a joint research and engineering laboratory (CEA, CNRS, Université Paris-Saclay, and Université de Versailles-Saint-Quentin) specializing in high-performance computing and numerical simulation.

You hold a PhD in computer science or another field, with experience in scientific computing.

You are proficient in several programming languages (Python, C/C++, or Fortran), with in-depth knowledge of parallel programming (GPU, multi‑threading, etc.). You have strong software engineering skills and at least some experience with standard collaborative development tools such as Git, GitHub, CMake, Docker, Spack, GTest, CTest, etc.

You are pragmatic and able to take initiative. Your analytical skills and ability to step back and take a broader perspective enable you to approach complex problems involving multiple constraints with confidence, including tight deadlines and major technical challenges.

You enjoy working as part of a team and have a particular interest in interdisciplinary collaborations involving multiple stakeholders, at the interface between applied mathematics, computer science, and physics applications. You have excellent written and oral communication skills, in both French and English.