DevOps Engineer for HEP GPU Benchmarks

DevOps Engineer for HEP GPU Benchmarks

European Organization for Nuclear Research (CERN)

November 8, 2026December 23, 2026GenevaSwitzerland
Job Description
Job Posting Organization:
CERN, the European Organization for Nuclear Research, was established in 1954 and is one of the world's largest and most respected centers for scientific research. With a mission to push the frontiers of science and technology, CERN employs around 2,500 staff members and collaborates with thousands of scientists from over 100 countries. The organization operates in multiple countries, focusing on particle physics and the fundamental structure of the universe. CERN is known for its innovative research and development in various fields, including computing, engineering, and technology, and it fosters a collaborative environment that values diversity and inclusion.

Job Overview:
As a DevOps Engineer for HEP GPU Benchmarks at CERN, you will play a crucial role in supporting the development, operation, and user support for the Worldwide LHC Computing Grid (WLCG) HEPScore benchmarking services. This position involves contributing to the next-generation benchmarking software stack that is essential for the High Energy Physics (HEP) community. You will be responsible for software development, containerization, service maintenance, performance analysis, and providing technical support to the WLCG user community. Your work will directly impact the ability of researchers to accurately measure and compare computing resources, which is vital for the ongoing success of the LHC experiments. This role requires a strong foundation in Python programming, containerization technologies, and DevOps practices, as well as a commitment to collaboration and communication with domain experts across the global WLCG collaboration.

Duties and Responsibilities:
  • Software Development: Actively contribute to the development, packaging, and distribution of the HEP benchmark software stack. This includes integrating, profiling, and validating production-level GPU application workloads from LHC experiment software, such as event generation, simulation, fast inference, and HLT.
  • Containerisation: Build, test, and maintain container images of HEP workloads using automated GitLab CI/CD pipelines to ensure efficient deployment and scalability.
  • Service Maintenance & Enhancement: Ensure the smooth operation of the core benchmarking infrastructure and data ingestion services using tools such as Puppet, GitLab CI/CD, ActiveMQ, Logstash, OpenSearch, Kibana, Apache Spark, and Grafana.
  • Performance Analysis: Collect, process, and analyze grid-wide benchmark data to evaluate performance scaling across diverse CPU/GPU architectures and server configurations, providing insights that drive improvements.
  • Technical Support: Provide technical support and documentation to the WLCG user community, ensuring that users can effectively utilize the benchmarking services and tools provided.

Required Qualifications:
  • Advanced Python Development: Solid experience in Python programming, including modular code structure, packaging, distribution, and testing.
  • Containerisation: Solid understanding of Docker and Apptainer/Singularity, along with familiarity with GPU container execution runtime environments.
  • DevOps & Infrastructure Automation: Proficiency with GitLab CI/CD pipelines, container registries, configuration management (Puppet), and deployment methodologies.
  • Linux Systems & Performance Profiling: Strong Linux administration and shell scripting skills, with experience in system metrics tracking such as CPU/GPU utilization, hardware performance metrics, and power monitoring.
  • Data Analytics Pipelines & Visualisation: Experience with monitoring and data analytics stacks such as OpenSearch/Elasticsearch, Logstash, Kibana, Grafana, or Apache Spark.

Educational Background:
Candidates must have a professional background in Applied Physics, Software Engineering, or a related field. The educational requirements include either a Master's degree with 2 to 6 years of post-graduation professional experience or a PhD with no more than 3 years of post-graduation professional experience. Additionally, candidates must be nationals of a CERN Member or Associate Member State and should not have previously held a CERN fellow or graduate contract.

Experience:
The position requires candidates to have a professional background that includes either a Master's degree with 2 to 6 years of relevant post-graduation experience or a PhD with a maximum of 3 years of relevant experience. This experience should be in fields related to applied physics, software engineering, or similar disciplines, demonstrating a solid foundation in the necessary technical skills and knowledge required for the role.

Languages:
Fluency in spoken and written English is mandatory for this position, as effective communication is essential for collaboration within the global WLCG community. Additionally, candidates should have a commitment to learning French, which is beneficial for integration into the CERN environment and for communication with local colleagues.

Additional Notes:
The contract duration for this position is 24 months, with the possibility of extension up to a maximum of 36 months. The working hours are set at 40 hours per week, and the job is fully onsite. The target start date for this position is January 1, 202
  • The role may involve stand-by duty and work during nights, Sundays, and official holidays as required by the needs of the organization. The job reference is IT-CE-LCG-2026-168-GRAP, and it falls under the field of Information Technologies with a benchmark job classification of 200020 - Computing Engineer. Compensation includes a monthly net stipend ranging from 6,372 to 7,004 Swiss Francs, depending on the candidate's degree, along with 30 days of paid leave per year, comprehensive health insurance coverage, family allowances, a relocation package, and opportunities for on-the-job and formal training, including language classes.
Apply now
Similar Jobs