We are looking for a candidate with a Master's degree, Engineer's degree or PhD in computer science, junior or senior, to join a team responsible for the packaging, deployment, and testing of supercomputing libraries for supercomputers.
The position is located at Maison de la Simulation team, in Saclay (near Paris), but our team is distributed in the following other locations:
- Inria Datamove team, located near Grenoble, in the French Alps
- Inria SED team, located near Bordeaux, close to the Atlantic Ocean
This work is part of the NumPEx project which is endowed with more than 40 million euros over 6 years, starting from 2023. This project aims to build a software stack for Exascale supercomputers related to the arrival in Europe of the first Exascale machine. The French supercomputer is expected for 2025. These machines will be among the most powerful in the world, used for traditional scientific applications and artificial intelligence workloads.
Our role in NumPEx is to design and implement an innovative packaging, deployment and testing strategy. Commonly used solutions show their limits in front of the complexity of supercomputers and applications, as well as the need for reproducibility for open science. Our goal is to build a solution based on a new generation of promising packaging tools: Guix, Nix, Spack, …
You will contribute to the design and implementation of the packaging and continuous integration strategy. You will participate in the deployment and testing of the infrastructure. Furthermore, you will also participate with user support and training activities around all these aspects.
Our packaging strategy is centered on the open source tools Guix, Nix and Spack. In direct contact with the development teams of these tools, with the supercomputer administration teams, and with our foreign counterparts (European, Japanese, American, etc.), you will participate in:
- the design of the packaging strategy of the NumPEx project
- the effort of packaging these libraries with the proposed tools
- the design of a package test and validation solution taking into account the specificities of supercomputers
- the development of a solution allowing non-administrator users to deploy NumPEx libraries on supercomputers
- training around all of these aspects for researchers and engineers
