PhD physicist with 7+ years experience in data science and low-latency machine learning (ML) for the CMS experiment at the CERN Large Hadron Collider.

My research at CERN was focused on large-scale data analyses to search for anomalous physics phenomena, and on implementing ultra-fast ML algorithms in the CMS hardware trigger to enable those searches. I built efficient BDT/GNN/TCN/AE models for μs-latency inference on FPGAs, developed custom methods for data-driven background modeling and signal-extraction, and was responsible for the CMS trigger calibrations.

And I'm now transitioning to industry! I'm seeking a position in data science, ML engineering or quantitative research. I want to work on problems with a more direct impact than fundamental science and learn new tools & practices, while still working with complex data and SOTA ML.

📧 peter.meiring@hetnet.nl · LinkedIn · Google Scholar

Most CMS Collaboration analysis code lives in CERN-internal repositories and cannot be shared publicly. But some representative technical work can be found in the links below:

• BDT electron-ID — merged into CMS software — the first fully demonstrated ML algorithm for the next-generation CMS hardware trigger (CMS Award 2023).
• Calorimeter calibrations — deployed in the CMS hardware trigger for 2025 data-taking.
• GNN training framework (L1DeepMETv2) — real-time energy regression in the next-generation CMS hardware trigger.
• Global-significance toolkit — significance from millions of pseudo-experiments, distributed on CMS Connect.

See also my Google Scholar. Note that CMS publishes collaboration-wide; a selection of the results I drove is listed here.

• DGNNFlow: A Streaming Dataflow Architecture for Real-Time Edge-based Dynamic GNN Inference in HL-LHC Trigger Systems — submitted to ACM TRETS (2026) · arXiv:2603.20364
• Search for new physics with compressed mass spectra in final states with soft leptons and missing transverse energy in proton-proton collisions at √s = 13 TeV — CMS-PAS-EXO-23-017, main analyser · CDS record
• Combined search for electroweak production of winos, binos, higgsinos, and sleptons in proton-proton collisions at √s = 13 TeV — Phys. Rev. D 109 (2024) 112001 · arXiv:2402.01888
• Electron Reconstruction and Identification in the CMS Phase-2 Level-1 Trigger — CERN-CMS-DP-2023-047 · CDS record
• Search for supersymmetry in final states with two or three soft leptons and missing transverse momentum in proton-proton collisions at √s = 13 TeV — JHEP 04 (2022) 091 · arXiv:2111.06296

• CMS Award 2023 for the first ML algorithm demonstrated for the Phase-2 Level-1 trigger upgrade.
• Shared Breakthrough Prize in Fundamental Physics (2025) with the CMS Collaboration.
• PhD Grant from the University of Zurich.

• Chengyu: Origins (in development) — a cross-platform mobile app on the origins of Chinese idioms, which I design and build while studying Mandarin in Beijing.
• The Fit Frontier — a science blog on the frontiers of fitness and health; I own, build, and write it.