SiPearl is the European fabless designer of sovereign secure high-performance energy-efficient CPUs for HPC, AI and data centres. These CPUs will help address strategic challenges in the fields of security, defence, medical research, energy, climate and engineering with a reduced environmental footprint.
In June 25, SiPearl completed the design of the most complex CPU ever designed in Europe, Rhea1. Featuring 80 Arm Neoverse V1 cores, with 61 billion transistors, it is currently in production at TSMC. Sipearl CPUs will equip the two first European exascale supercomputers belonging to EuroHPC JU: Rhea1 will be integrated into the JUPITER machine based in Germany and Rhea2 will be part of Alice Recoque in France.
Incubated within the European Processor Initiative (EPI) consortium and seed-funded by the European Union, SiPearl employs almost 200 people in :
France (Maisons-Laffitte, Grenoble, Massy, Sophia Antipolis),
Spain (Barcelona)
and Italy (Bologna)
Following a €130 million Series A, the company has launched its Series B round.
SiPearl is developing high-performance processors dedicated to European supercomputers. In this context, the intern will contribute to the optimization of HPC and AI workloads by leveraging advanced architectural features such as Scalable Vector Extension (SVE) vectorization and heterogeneous memory systems.
During this internship, you will:
Evaluate the maturity of the AI software stack used for benchmarking, including frameworks such as MLPerf and similar benchmarks.
Test and optimize various machine learning frameworks, including TensorFlow, PyTorch, and ONNX Runtime, as well as mathematical libraries and different parallelization strategies.
Conduct comparative performance studies on AArch64 and x86 architectures.
Perform performance analysis and projections for future generations of SiPearl processors.
Student in the final year of an engineering school or pursuing a Master's degree in electronics, computer engineering, or a related field
Experience in programming with C, C++, and Python
Experience with machine learning frameworks such as TensorFlow or PyTorch
Understanding of machine learning workflows, including training, inference, and fine-tuning
Knowledge of parallelization techniques for high-performance computing.
Familiarity with modern AI models and machine learning concepts.
Knowledge of ARM architecture is a plus.
Good written and spoken English
📍 Location -> Castelldefels
SiPearl is the European fabless designer of sovereign high-performance energy-efficient processors for HPC, AI and data centres. These processors will help address strategic dual-use challenges in the fields of security, defence, medical research, energy, climate and engineering with a reduced environmental footprint.
In June 2025, SiPearl completed the design of the most complex processor ever designed in Europe, Rhea1. Featuring 80 Arm Neoverse V1 cores, with 61 billion transistors, it is currently in production at TSMC in Taïwan and will be available for sampling in early 2026. Rhea1 processors will equip JUPITER, the first European exascale supercomputer owned by the EuroHPC JU and operated by the Jülich Supercomputing Centre in Germany.
Incubated within the European Processor Initiative (EPI) consortium and seed-funded by the European Union, SiPearl employs 200 people in France, Spain and Italy. Following a successful €130 million Series A, the company is launching its Series B round.
