Sioni Summers

profile photo

👤 Biography

I’m an applied physicst at CERN working on the Level 1 Trigger of the CMS Experiment at the LHC. For the Phase 2 Upgrade I develop fast and efficient physics reconstruction algorithms for FPGAs. I’ve contributed to track finding, vertex reconstruction, particle flow, pileup subtraction (PUPPI), jet reconstruction, electron identification, and providing a platform for particle-based algorithms.

I also develop algorithms and tools for machine learning in the trigger. I helped to deploy the first ML seed in the CMS trigger during LHC Run 3 in 2024, the anomaly detection trigger AXOL1TL. For the Phase 2 Upgrade of CMS I’m involved in several projects to enhance our data taking with ML, like jet tagging. I’m a task leader in the Next Generation Triggers project at CERN, leading efforts on deeply integrating ML into the CMS Phase 2 Trigger. On the ML tools side I created and maintain conifer for BDT inference on FPGAs, and I’ve previously been coordinator of hls4ml for NN inference on FPGAs.

I’m motivated to apply the techniques and technology we develop at CERN for fast ML inference in other areas as well. At the moment I’m working on a project, called Edge SpAIce, to use these tools for the detection of plastics pollution in the ocean onboard Earth Observation satellites. I’ve previously worked on a collaboration with autonomous vehicle company Zenseact.


✨ I’m hiring ✨

Join us to push the boundaries of real-time Machine Learning ML in one of the most demanding computing environments in the world. You will develop cutting-edge ML models for the CMS Level-1 Trigger – an ultra-low-latency, FPGA-based system responsible for selecting the most interesting LHC collisions in real-time. You will help design the next generation of trigger algorithms for the High Luminosity LHC era by co-training ML models across different systems to maximise physics performance while optimising information flow, bandwidth, and on-device resource usage. This includes developing and scaling MLOps workflows, integrating ML models into FPGAs, and delivering demonstrators that validate full-chain performance from training and physics performance to on-hardware deployment. This position is part of the NextGen Triggers (NGT) project, a 5-year collaboration between LHC experiments and the CERN Research and Computing Departments.

👉 Read more and apply here

Get to know some of the team you’ll be working with in the video below:


🚀 Projects

Check the projects page for positions for which I’m hiring. Below are listed some of the things I’m working on:


📚 Other reading


📄 Selected publications

J-F. Schulte et al, hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware, 2025 preprint arXiv
S. Schaefer et al, Advancing the CMS Level-1 Trigger: Jet Tagging with DeepSets at  
the HL-LHC, 2025 preprint arXiv
N. D’Abbondanza, et al, Edge SpAIce: Deep Learning Deployment Pipeline for Onboard Data Reduction on Satellite FPGAs, 2025 IPDPSW DOI, link
S. Summers et al, Reconstructing jets in the Phase-2 upgrade of the CMS Level-1 Trigger with a seeded cone algorithm, 2024 EPJ Web of Conf. DOI, link, arXiv
P. Odagia et al, Ultrafast jet classification at the HL-LHC, 2024 MLST DOI, link, arXiv
N. Ghielmetti et al, Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml, 2022 MLST DOI, link, arXiv
C.N. Coelho et al, Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors, 2021 Nature Machine Intelligence DOI, link, arXiv
J. Ngadiuba et al, Compressing deep neural networks on FPGAs to binary and ternary precision with hls4ml, 2021 MLST DOI, link, arXiv
S. Summers et al, Fast inference of Boosted Decision Trees in FPGAs for particle physics, 2020 JINST 15 DOI, link
R. Aggleton et al, An FPGA based track finder for the L1 trigger of the CMS experiment at the High Luminosity LHC, 2017 JINST DOI, link
S. Summers et al, Using MaxCompiler for the high level synthesis of trigger algorithms, 2017 JINST DOI, link


💬 Posts