Experience

 
 
 
 
 

Research Assistant

Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen

Oct 2019 – Apr 2025 Aachen

PhD: Neuro-inspired Learning Mechanisms for Efficient and Robust Neural Networks

  • Designed and implemented a cluster of 35 FPGAs for neuroscience simulations, developing AXI-based RTL modules (Xilinx toolchain, System Verilog) and embedded software (C/C++)
  • Developed control scripts (TCL, Python, shell) and firmware (C++, Python), automating deployment, testing, and monitoring of the FPGA cluster (Linux, Git, CI)
  • Project lead for the cluster project: Coordination of research staff and students, organization of workflows, weekly meetings, and liaising with suppliers
  • Conducted research in the optimization of brain-inspired deep learning for efficient Edge AI and AI hardware acceleration
  • Supervised design, schematic validation and test of PCBs for high-frequency inter-FPGA communication (PCIe, SATA) with KiCad
 
 
 
 
 

Student Research Assistant

Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen

Sep 2018 – Jan 2019 Aachen
  • Converted VHDL-based RTL modules for a DCF77 radio receiver to Verilog & deployed them on Intel Altera Cyclone FPGAs
  • Designed and implemented a bit-precise verification MATLAB toolbox for an Intel Stratix FPGA AI accelerator
 
 
 
 
 

Intern

European Space Operations Centre, European Space Agency

Feb 2018 – Jul 2018 Darmstadt

Feasibility Study for a Robotic Arm Simulator to Evaluate Operational Concepts

  • Developed a ROS-based C++ simulation for studying man-machine interaction in a lunar mission scenario
  • Organized and conducted user tests to assess both study and simulator design and perform requirement analyses
 
 
 
 
 

Student Research Assistant

Institute for Man-Machine-Interaction, RWTH Aachen

Oct 2015 – Jun 2017 Aachen
  • Developed a MATLAB toolbox for controlling Lego Mindstorms EV3 robots via USB and Bluetooth
  • Participated in the organization of the annual lab ‘MATLAB meets Mindstorms’ where 400-600 electrical engineering students program EV3 robots

Education

 
 
 
 
 

Dr. Ing. (PhD) in Electrical Engineering

Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen

Oct 2019 – Present Aachen
Topic: Neuro-inspired Learning Mechanisms for Efficient and Robust Neural Networks
 
 
 
 
 

MSc. Electrical Engineering, Information Technology and Computer Engineering

RWTH Aachen

Oct 2016 – Jul 2019 Aachen
  • Master thesis: Mapping ANNs to Monadic Signed-Digit Operations (ANN FPGA accelerator design)
  • Selected courses: Operating Systems, Embedded Systems, DSP Design, Microcontrollers, Compiler Engineering
  • Exchange semester at KTH Stockholm (2017)
 
 
 
 
 

BSc. Electrical Engineering, Information Technology and Computer Engineering

RWTH Aachen

Oct 2013 – Sep 2016 Aachen
  • Bachelor thesis: Automated Detection of Facial Regions for Stress Analyses in Mice

Publications

More on Google Scholar

Balanced and Efficient Spiking Neural Networks

In IJCNN 2025
Translating novel insights from computational neuroscience into neuromorphic computing, we show how tightly balanced Spiking Neural Networks outperform existing networks in efficiency, robustness while maintaining competitive accuracy.
Code

NoisyDECOLLE: Robust Local Learning for SNNs on Neuromorphic Hardware

In ICMLA 2023
NoisyDECOLLE is a Python framework for assessing the robustness of SNNs trained with local learning rules inspired by three-factor learning and synaptic plasticity.
PDF Code DOI

neuroAIx: FPGA cluster for reproducible and accelerated neuroscience simulations of SNNs

In NorCAS 2023
Designing and implementing the neuroAIx FPGA cluster, we show how a combination of novel communication topology, local synchronization algorithm and design paradigms like maximizing neuron-per-node density lead to a neuromorphic system that enables high-speed, deterministic and efficient neuroscience simulations.
PDF Code DOI

neuroAIx-Framework: design of future neuroscience simulation systems

In Frontiers in Computational Neuroscience
The neuroAIx framework is a collection of C++-based simulation tools and hardware platforms to evaluate novel hardware concepts for neuroscience experiment accelerators.
PDF DOI

From quantitative analysis to synthesis of efficient binary neural networks

In ICMLA 2020
We derive an approach on how to systematically design cost-efficient BNNs, with novel methods like hybrid ternarization and a hardware-based cost estimation leading to BNNs more efficient that existing ones without compromising accuracy.
PDF Code DOI

Extracurriculars

Executive board and founding member

neuroAIx e.V. Dec 2022
Coordinated alumni meet-ups and developed the club website, fostering interdisciplinary networking.

Technical team lead

Engineers Without Borders, RG Aachen Dec 2020 – Oct 2023
Developed solutions to improve sanitation infrastructure and access to clean water wells in rural Cameroon.

Supervisor

Undergraduate Research Opportunities Program Jul 2017 – Dec 2017
Supervised undergraduates from USA and Canada in hands-on research and academic development