GPU & ML Developer for Reconstruction and Simulation (EP-ALI-SC-2026-106-GRAP)
On-site · Genève, Geneva, Switzerland
Job Summary
GPU & ML software developer to maintain, develop, and commission ML-based GPU event reconstruction code for the ALICE experiment, including ML-based clusterisation and TPC track seeding. Contribute to ALICE's Monte Carlo production ecosystem and simulation frameworks, focusing on workflow automation, validation, and integration of ML and GPU components. Develop and operate automated solutions for MC production, job orchestration, and ML-driven anomaly detection; track activities in optimisation and modernisation of simulation/reconstruction frameworks (Geant, AliceO2) with ML-driven acceleration. Investigate components of the ALICE computing chain that could benefit from ML/GPU and develop prototypes. Requires strong C++ on Linux, CUDA or HIP, ONNXRuntime, debugging/profiling tools, and ability to work in a team. English, with a commitment to learn French. Eligibility: National of a CERN Member or Associate Member State; Master’s with 2–6 years or PhD with ≤3 years; never had a CERN fellow/graduate contract. Job duration: 24 months, onsite working hours 40/week, with stand-by duties; start around 01-August-2026; relocation package included. STEM-friendly, international environment with a focus on cutting-edge physics computing.
Required Qualifications
- Master's degree with 2 to 6 years post-graduation
- PhD with no more than 3 years post-graduation
- Experience with HEP event reconstruction code
- GPU programming and ML training/inference
- C++ on Linux
- CUDA or HIP
- ONNXRuntime
- GDB and perf
- English; willingness to learn French
Desired Qualifications
- Master's degree with 2 to 6 years of post-graduation professional experience
- PhD with no more than 3 years of post-graduation professional experience
- Experience with high energy physics (HEP) experiments event reconstruction code
- GPU programming and ML training and inference
- Practical experience debugging large distributed applications
- Strong knowledge of C++ on Linux
- Knowledge of CUDA or HIP
- Knowledge of ONNXRuntime
- Knowledge of debugging and profiling tools (e.g., GDB, perf)
- Ability to work in a team
- English (spoken and written); willingness to learn French
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.