ML on Edge Hardware
Electron/Photon Classification BDT on FPGA
The first ML algorithm for the CMS hardware-trigger upgrade: a BDT running in FPGA firmware at 100 ns latency. CMS Award 2023
XGBoostconiferBDTXilinx VU13P
Coming soon
My experience, in a nutshell
01
Large-scale Data Analysis
I analyze PB-scale collision data to search for New Physics phenomena, such as Dark Matter and Supersymmetry, designing experimental strategies, developing data-driven models, and advanced statistical interpretations.
02
AI on Edge
I build efficient ML/DL models for ultralow-latency inference on edge-hardware (FPGAs & ASICs) to perform classification, regression, compression or reconstruction tasks in real-time applications, such as the CMS trigger system (L1T).
03
Sensor System Calibration & Ops
Working with complex machines or measurement systems is always exciting! During my (post)doctoral positions at UZH and CMU, I operated the CMS experiment and was responsible for the production calibration pipeline for the L1T calorimeter objects.
Selected work
Research Projects
A grasp of my activities at the frontiers of energy and luminosity.
Physics & Data Science
Searching for Supersymmetry & Dark Matter
Data-driven statistical modeling on petabyte-scale collision data to find what is Beyond the Standard Model of particle physics.
PythonROOTStatistical modelingLikelihood fits
Coming soon
Let's work together!
I'm always open for exciting opportunities in the area of data science and deep-tech, also outside of the physics domain. Have an interesting idea? I'd love to hear about it!