Category: cdd

The French Commissariat à l’Energie Atomique (CEA) is inviting applications for an HPC engineer position at Maison de la Simulation, Saclay, France, with a focus on C++ parallel programming for high-end HPC applications.

This is a 20 months position within the long-running Energy-oriented Center of Excellence (EoCoE-III), an ambitious, Europe-wide project that develops exascale lighthouse applications targeting critical energy sectors.
The successful candidate will join a vibrant and diverse team working on the cutting edge of High Performance Computing (HPC) technologies.

To apply, please send your application (CV and covering letter) to contact@eocoe.eu
If you have any questions about the position, please use the same address.

Context

The Energy-oriented Centre of Excellence for exascale HPC applications (EoCoE-III) aims to support Europe’s transition to decarbonized energy by utilizing advanced computational methods. Building on the success of two previous projects, EoCoE-III focuses on four key energy domains: Energy Materials, Water, Wind, and Fusion. The project brings together 18 partners from six countries, including three top European supercomputing centers. EoCoE-III will develop new modeling capabilities to overcome performance challenges and demonstrate the benefits of HPC for the energy industry, with applications like photovoltaic device design, wind farm modeling, and plasma interactions in fusion reactors.

Position Overview

The candidate will contribute to the fifth work package of the EoCoE-III project, focusing on performance optimization and portability and on testing new programming models and new hardware.
He/she will be working closely with the WP5 team in CEA and in close collaboration with Dr. Harald Koestler (FAU Erlangen-Nürnberg).
This role offers the unique opportunity to be part of a large-scale international project aimed at driving the next generation of energy research and innovation through state-of-the-art HPC methodologies.
He/she will have access to innovative and high-end HPC hardware, in particular through collaboration with the major vendors and be part of a team with unique expertise on the topics.

Key Responsibilities

Contribute to the performances evaluation of the EoCoE-III lighthouse application codes on
exascale systems.

• Contribute to the performances evaluation of the EoCoE-III lighthouse application codes on exascale systems.
• Test small kernels extracted from these applications on prototype hardware.
• Test innovative programming models.
• Collaborate with a team of international experts in the field of performance monitoring and optimization.
• Contribute to research publications and presentations at international conferences.
• Work closely with other teams within the EoCoE-III consortium, including partners across Europe, to achieve project goals.
• Engage in regular reporting and communication with the project leadership.

Opportunities and Benefits

Join a leading European research institution with a reputation for excellence and innovation.

• Join a leading European research institution with a reputation for excellence and innovation.
• Work alongside a dynamic and international team of experts in HPC and energy research.
• Be part of an ambitious and vast international project that addresses critical energy challenges.
• Access to cutting-edge HPC technologies and resources at Maison de la Simulation.
• Professional growth and networking opportunities through collaboration with top-tier researchers and institutions across Europe.
• CEA offers competitive salaries depending on your qualifications and experience.
• Up to 3 remote working days per week.
• 75% reimbursement on public transport and a free transport network throughout the Ile-de-France region.
• An attractive supplementary pension scheme and several company savings plans.
• 5 weeks’ paid holiday and 4 weeks’ RTT (days off) per year.

Qualifications

You have a Ph.D. in Computer Science, Applied Mathematics, Physics, or a related field with a focus on HPC, parallel programming, or performance optimization.
You already have an experience in C++ programming, particularly in a parallel computing context.
You are familiar with HPC environments and performance profiling tools.
You are able to work independently and collaboratively in a multidisciplinary and multicultural environment.
You have excellent communication skills in English.
Knowledge of French is a plus but is not required.

Application Process

Interested candidates are invited to submit the following documents:

• A detailed CV including a list of publications.
• A cover letter explaining your interest in the position and how your experience aligns with the
  requirements.
• Contact information for at least two academic references.

Deadline for Application: Applications will be evaluated from 20/01/2025 and until the position isfilled.
Please send your application materials to contact@eocoe.eu with the subject line “HPC engineer Application – EoCoE-III.”

CEA is recruiting a C++/HPC expert for two years to join the CExA “Moonshot” project team to develop new methods and tools to optimize the performance of portable kernels implemented using the Kokkos library. As a use-case, these tools and techniques will be demonstrated in the Dyablo code, a novel HPC code for simulating astrophysical fluids, from stellar interiors to cosmological simulations.

To apply, please send your application (CV and cover letter) to contact@cexa-project.org. If you have any questions about the position, please use the same address. Applications will be assessed from now and until the position is filled.

Context

Europe is investing to build Exaflop supercomputers in the coming years, including the Alice Recoque one in France, at CEA in 2025. These machines will be heterogeneous, and based on GPUs of various brands and architectures. Ensuring performance and portability under these conditions is certainly one of the most significant challenges for Exascale. To address this, CEA is investing heavily in an ambitious “Moonshot” project: CExA. Part of CExA is contributing to the Kokkos C++ GPU programming model to add new features required by European codes and ensure that it is compatible with European supercomputers so researchers can exploit these architectures for their scientific applications. One of these scientific applications is the Dyablo code developed since 2020 at CEA for simulating astrophysical fluids with adaptive mesh refinement. This code was written from the start using Kokkos and is thus already facing optimization challenges that many other codes will face in the coming years.

In this context, CEA opens a two-year engineering position to develop new methods and tools to optimize large applications based on Kokkos. This project will use Dyablo as a use case to test and validate the optimization methods. This project will involve the development team of Dyablo as well as key players of the CExA Moonshot :

• The DRF’s software and engineering department of the Institute of research into the fundamental laws of the Universe (IRFU) is the main developer of the Dyablo code.
• Maison de la Simulation (https://www.mdls.fr) of the DRF is a joint research and engineering laboratory of CEA, CNRS, Univ. Paris-Saclay and UVSQ specialized in high-performance computing and numerical simulation.
• The DES’s software engineering department for simulation brings together three laboratories that address the issues of the simulation environment, AI and data science, high-performance computing, and numerical analysis.
• The DSSI of the DAM manages activities in computer science, applied mathematics, and information systems, covering a broad spectrum from definition and design to user services.

Mission

As part of both the Dyablo and CExA teams, you will develop tools and methods to optimize the performance of Kokkos’ applications and apply them to Dyablo.

Your mission will include:

• Development of new methods for the optimization of large applications using Kokkos:
  • Design and develop a tool to extract kernels from a large code while capturing inputs and outputs to generate a self-consistent mini-app that can be easily profiled and optimized separately from the rest of the code.
  • Develop a tool to profile and analyze the performance of the mini-apps extracted by the previous tool. This profiler should be able to provide insights like a profiling software such as Vtune.
  • Design an auto-tuning method to fine-tune any free parameter of the mini-app to gain the optimal performance on a given target architecture.
• Application of this new set of tools and methods on the Dyablo code:
  • Profile the hotspots of the code and generate a set of self-consistent mini-apps for different types of simulations and architectures.
  • Investigate the optimization potential of the code on different architectures such as Nvidia GPUs, AMD CPUs, and GPUs or Intel CPUs.

Salary and benefits

Fiche de poste PTC – SN – MOONK

• The CEA offers salaries based on your degrees and experience.
• This position offers several advantages: the possibility to join collaborations with other European laboratories, the United States and Japan,
• Numerous opportunities to travel internationally (exchanges, conferences, workshops and more)
• Up to 3 days of telecommuting per week
• Reimbursement of up to 75% of public transport cards and a free transport network throughout the Ile-de-France region,
• Interesting complementary health insurance and several company savings plans,
• 5 weeks of paid vacation and 4 weeks of RTT per year.

Join the CEA’s ambitious GenEx project and contribute to the development of a genomic computing library adapted to GPU and exascale systems. We are recruiting an HPC engineer for a period of 1 year (renewable for a second year) to work at our CEA Saclay site near Paris.

To apply, please send your application (resume and cover letter) to edouard.audit@cea.fr. You can use this same address for any questions concerning the offer. Applications will be evaluated from mid-September until the position is filled.

Context

The objective of GenEx is to develop, through a collaboration between the Joliot Institute and the Maison de la Simulation (MdlS), an innovative, versatile, and highly efficient code to interpret genomics experiments, initially focusing on DNA repair mechanisms that are the subject of many experiments at Joliot. This requires very intensive computations, making it essential to have a code capable of fully utilizing the computational power of exascale architectures.

The collaboration between Joliot and MdS will combine top-level expertise in computer sciences and genomics. Thus, GenEx will implement a tool that will represent a significant advancement over existing tools. Traditional algorithms handling this type of problem are based on Monte-Carlo methods involving conditional events for each agent involved in the process. This approach is particularly unsuitable for GPU-type architectures. Therefore, a new algorithmic approach has been conceived. This approach handles agent interactions in batches, enabling highly efficient GPU code.

The recruited engineer will be co-supervised by MdS and Joliot to implement this new approach. To achieve a portable, efficient code that fully exploits GPUs, the core of the code will be developed using the Kokkos library, for which there is strong expertise at MdS and within the CExA project. Subsequently, a Python interface will be established to make the code easily usable by the community of biologists/bioinformaticians/biophysicists, knowing that ultimately GenEx could interest many teams in various fields of application.

The initial applications will focus on yeast, whose genome contains 6k genes each with 300 to 3k base pairs. To interpret experimental results, it is necessary to simulate several million experiments for each gene with a model having about ten free parameters (>100Mh with current methods). One of the long-term objectives will be to conduct a similar study on the human genome (20k genes with 300 to 3M base pairs) on the Exascale machine soon to arrive at CEA. PTC funding is essential to initiate the implementation of the code, and the significant results thus obtained will have a substantial leveraging effect for further development.

Mission

As part of the GenEx team you will be responsible to develop and test the new software in collaboration with experts of genomics at Joliot and of computer science at MdS.

Your mission will include:

• Discussions and set-up of the physical models to modelise DNA repairs
• Test of various algorithms to solve these models
• Development of an highly efficient code, based on Kokkos, to implement the previous

Skills

You have a master and/or an engineering degree in computer science and:

• You have a good knowledge of C++.
• You have skills in software engineering. You are familiar with common development environments and associated tools.
• Knowledge of parallel programming (GPU, multi-threaded, etc.) is a plus, especially with the Kokkos library or equivalent.
• You are autonomous and you wish to be part of an interdisciplinary work team.

Salary and benefits

The CEA offers salaries based on your degrees and experience. This position offers several advantages:

• Numerous opportunities to travel internationally (exchanges, conferences, workshops and more).
• Up to 3 days of telecommuting per week.
• Reimbursement of up to 75% of public transport cards and a free transport network throughout the Ile-de-France region.
• An interesting complementary health insurance and several company savings plans.
• 9 weeks of paid vacation per year.

Overview

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 (https://mdls.fr), in Saclay (near Paris), but our team is distributed in the following other locations:

• Inria Datamove team (https://team.inria.fr/datamove), located near Grenoble, in the French Alps
• Inria SED team (https://sed-bso.gitlabpages.inria.fr), located near Bordeaux, close to the Atlantic Ocean

This work is part of the NumPEx project (http://www.numpex.fr) 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 (https://top500.org), 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, …

• Contact: Benoît Martin (bmartin@cea.fr) & Bruno Raffin (bruno.raffin@inria.fr)
• Duration: 3 years
• Start date: ASAP

Assignment

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 (https://hpc.guix.info), Nix (https://nixos.org) and Spack (https://spack.io). 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:

1. the design of the packaging strategy of the NumPEx project
2. the effort of packaging these libraries with the proposed tools
3. the design of a package test and validation solution taking into account the specificities of supercomputers
4. the development of a solution allowing non-administrator users to deploy NumPEx libraries on supercomputers
5. training around all of these aspects for researchers and engineers

Skills

Master’s degree, Engineer’s degree or PhD, beginner or confirmed (salary adjusted according to experience) in computer science.

The essential expected skills are:

• Good practice of Unix/Linux system and system administration
• Good programming experience (C/C++, Python)
• Experience with software compilation and installation chains, version management tools, testing and continuous integration (CMake, Git, GitHub, GitLab, …)
• The work being performed in an international context, a good practice of technical English (written and oral) is expected (proficiency in French is not compulsory), as is a taste for team work.

Any additional skill related to package managers (Guix, Nix, Spack, apt, rpm, pip, …), containers (Singularity/Apptainer, Docker, …) or open source development are a plus. An initial training time will be provided to complement the missing skills. You will integrate an academic research environment which will give you, throughout your contract, the opportunity to complete your training on cutting-edge technologies.

Application

To apply, please send the following elements to Benoît Martin and Bruno Raffin:

• a curriculum vitae
• a motivation letter
• references from people we can contact to certify your qualities
• a recent internship or thesis report
• links to software contributions

Salary and benefits

The CEA offers salaries based on your degrees and experience. This position provides several advantages:

• The possibility of joining collaborations with other European laboratories, the United States, and Japan
• Numerous opportunities to travel internationally (exchanges, conferences, workshops and more)
• 5 weeks of paid vacation and 4 weeks of RTT per year, and up to 2 days of remote work per week.
• Reimbursement of up to 75% of public transport cards and a free transport network throughout the Ile-de-France region
• Complimentary health insurance and several company savings plans

Overview

Maison de la Simulation offers 2-3 engineer positions to join the newly created PDI team.

• Contact: Yushan Wang (yushan.wang@cea.fr) & Benoît Martin (bmartin@cea.fr)
• Duration: 3 years
• Start date: ASAP

Application

Candidates must have at least a Master’s degree or equivalent in Computer Science, Applied Mathematics, or other relevant fields. A PhD degree and working experience in a relevant domain are appreciated. Good programming skills are required.

Applications should be sent to Yushan Wang and Benoît Martin. They should include:

• a curriculum vitae
• a motivation letter
• at least two referees with their email addresses
• links to Masters/PhD thesis and publications
• links to software contributions

Context

With the increasing complexity of numerical simulation codes, new approaches are required to analyze the ever-growing amount of data. This requires coupling up-to-date data analysis libraries with the existing highly optimized numerical simulation codes. The PDI Data Interface code coupling library is designed to fulfill this goal.

The open-source PDI Data Interface library is designed and developed for process-local loose coupling in high-performance simulation codes. PDI supports the modularization of codes by inter-mediating data exchange between the main simulation code and independent modules (plugins) based on various libraries. It is developed in modern C++ and offers C, Fortran, and Python application programming interfaces.

PDI offers a reference system similar to Python or C++’s shared_ptr with locking to ensure coherent access by coupled modules. It provides a global namespace (the data store) to share references and implements the Observer pattern to enable modules to react to data availability and modifications. It implements a metadata system that can specify a dynamic type for references based on the value of other data (e.g., array size based on the value of a shared integer). Codes using PDI’s declarative API expose the buffers in which they store data and trigger notifications when significant steps in the simulation are reached. Third-party libraries such as HDF5, SIONlib, or FTI are wrapped in a PDI plugin. A YAML configuration file is used to interleave plugins and additional code without modifying the original application.

Another aspect we explore with PDI is in-situ data analysis, which performs numerical analytics during the simulation. This is necessary due to the ever-growing gap between file system bandwidth and compute capacities. To this end, we are developing the Deisa plugin. This plugin is based on the open-source Dask framework and allows us to transfer data to dedicated processes to perform in-situ analysis.

One of our goals is to establish a feedback mechanism between the in-situ data analysis and the numerical simulation. This allows better resource allocations and on-the-fly simulation monitoring. Another aspect that in-situ analysis enables is using AI methods for HPC and HPDA. For instance, we can have unsupervised detection of rare events during the simulation, which can greatly reduce the amount of produced data, thus reducing stress on the file system.

Work environment

At Maison de la Simulation laboratory, you will join a group of engineers and scientists focusing on all aspects of high-performance computing (HPC). You will have the opportunity to collaborate with PDI users and to introduce new features in the PDI plugin family. As a member of the PDI team, you will also have the opportunity to exchange with the developers of other HPC codes to enrich your skills in HPC code development. To validate your developments, you will be provided with access to the top European supercomputers (Adastra, Jean-Zay, etc.).

Work content

As a member of the newly created PDI team, your primary focus will be developing and maintaining the PDI library.

• Develop core functionalities and new plugins for PDI
• Develop the Deisa library
• User-support
• Organize training sessions
• Library packaging and deployment

Skills

The successful candidate will master the following skills and knowledge:

• Proficiency in modern C++ (C++14 and above)
• Software engineering and library design
• Modern development environment (Linux, git, CMake, etc.)
• Communication (writing, presenting, and training)
• Team-work and integration in an international environment

In addition, the following will be considered a plus:

• Data analysis libraries such as Dask
• Knowledge and experience with Python, Fortran and/or GPU computing
• HPC and parallel libraries such as OpenMP and MPI
• HPC parallel IO libraries such as HDF5 or NetCDF
• Experience with supercomputer tools (slurm, sbatch, etc), packaging and deployment

Salary and benefits

The CEA offers salaries based on your degrees and experience. This position offers several advantages:

• The possibility of joining collaborations with other European laboratories, the United States, and Japan
• Numerous opportunities to travel internationally (exchanges, conferences, workshops and more)
• 5 weeks of paid vacation and 4 weeks of RTT per year, and up to 2 days of remote work per week
• Reimbursement of up to 75% of public transport cards and a free transport network throughout the Ile-de-France region
• Complimentary health insurance and several company savings plans

References

• Maison de la Simulation: https://mdls.fr/
• PDI: https://pdi.dev/
• Deisa: https://github.com/pdidev/deisa