Software developer GPU (EP-AIP-SDS-2025-27-GRAP)

Job Description

Your responsibilities

Join our team at the ALICE experiment within the CERN Large Hadron Collider (LHC) to develop high-performance computing code for data processing.

ALICE is pioneering the usage of GPUs for the online processing of the TPC in Run 3 and meanwhile also partly in offline reconstruction. In order to better leverage the available GPU compute resources, we aim to improve our GPU code and port more processing steps to GPU.

The first reconstruction passes of the heavy ion data of 2023 allow us to benchmark our event reconstruction code, and we intend to tune it better for real data. In addition, the processing of real data always reveals corner cases not covered by simulations, which must be dealt with. Your overall task will be to develop GPU and event reconstruction code for ALICE as well as to improve and maintain the existing code.

Responsibilities:

• Work in a small team of experts on the ALICE GPU code and event reconstruction code.
• Improve the integration of the GPU code into the CI and develop benchmarks and performance monitoring tools.
• Port more event reconstruction steps to the GPU to improve the resource utilization during offline processing.
• Benchmark and improve the (general, CPU and GPU) event reconstruction code with real data, in particular with respect to clustering and tracking.
• Help debugging problems appearing in event reconstruction during offline processing.

If you're passionate about GPU programming, advancing high-performance computing and contributing to groundbreaking research in particle physics, we encourage you to apply. Join us at the forefront of innovation in LHC data processing.

Your profile

Skills

Required:

• C++ Programming language
• Operating system: Linux
• Experience with GPU programming
• Experience with debugging tools like GDB
• Experience with high energy physics experiments event reconstruction code (e.g. clustering or tracking)

Advantageous:

• Knowledge of the mathematical / statistical methods used for track reconstruction, e.g. Kalman filter
• Experience with the HIP, CUDA, and OpenCL GPU languages.
• Experience with modern C++ (e.g. C++20).
• Experience with profiling tools like perf and valgrind, e.g. for finding compute hot spots or memory leaks.
• Experience with high performance computing (HPC).

Eligibility criteria:

• You are a national of a CERN Member or Associate Member State .
• You have a professional background in Computer Science or Physics (or a related field) and have 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.
• You have never had a CERN fellow or graduate contract before.

Additional Information

Job closing date: 17.03.2025 at 23:59 hrs CET.

Contract duration: 24 months, with a possible extension up to 36 months maximum.

Working hours: 40 hours per week

Job flexibility: Hybrid

Target start date: 01-May-2025

This position involves:

• Participation in a regular stand-by duty, including nights, Sundays and official holidays.
• Work during nights, Sundays and official holidays, when required by the needs of the Organization.

Job reference: EP-AIP-SDS-2025-27-GRAP

Field of work: Software Engineering and IT

Benchmark job: 200020 - Computing Engineer

What we offer

• A monthly stipend ranging between 6287  and 6911  Swiss Francs per month (net of tax).
• Coverage by CERN's comprehensive health scheme (for yourself, your spouse and children), and membership of the CERN Pension Fund.
• Depending on your individual circumstances: installation grant; family, child and infant allowances; payment of travel expenses at the beginning and end of contract.
• 30 days of paid leave per year.
• On-the-job and formal training at CERN as well as in-house language courses for English and/or French.

About us

At CERN, the European Organization for Nuclear Research, physicists and engineers are probing the fundamental structure of the universe. Using the world's largest and most complex scientific instruments, they study the basic constituents of matter - fundamental particles that are made to collide together at close to the speed of light. The process gives physicists clues about how particles interact, and provides insights into the fundamental laws of nature. Find out more on http://home.cern.

We are on a Quest. A Journey into discovery like no other. Bring your expertise to our unique work and develop your knowledge and skills at pace. Join world-class subject matter experts on unique projects, in a Quest for greater knowledge and deeper understanding.

Begin your CERN Quest. Take Part!

Diversity has been an integral part of CERN's mission since its foundation and is an established value of the Organization. Employing a diverse workforce is central to our success.