I design receivers that pull clean information out of noisy signals, in radios, networks, and even plants.
Who's behind the receiver.
Telecommunication engineer and AI software developer experienced in software development, machine learning, and signal processing for communication systems. A fast learner who tackles complex problems with persistence and analytical rigor to deliver precise, dependable solutions. Proactive and adaptable, I thrive in diverse teams and continuously expand my technical expertise. Highly self-driven and quick to master unfamiliar domains, I take full ownership of challenging problems and see them through to robust, well-engineered solutions.
I apply communication and information theory to biological and nanoscale systems. My focus is receiver design: extracting reliable information from noisy biological signals, with interests in bioelectrical and molecular communication, nanonetworks, and machine-learning-based detection that is accurate and light enough to run in real time.
My path, read like a logic analyzer: each line goes high while that thing was active.
Using communication theory on biological signals. The plant is the transmitter; I design the receiver.
Proceedings of the 13th ACM International Conference on Nanoscale Computing and Communication (NanoCom '26)
This paper treats plant stress detection as a receiver-side decoding problem over a biological communication channel. The plant acts as a biological transmitter whose electrophysiological signals encode its responses to environmental stress. We propose a receiver architecture and evaluate it on electrophysiological recordings under multiple stress conditions.
Industry-linked engineering projects at Politecnico di Milano, done together with Nokia.
Assigns ODUs to multi-carrier transponder framers under hardware constraints to improve optical data transmission. I implemented and compared six optimization methods, with smart traffic generation and performance visualizations.
MATLAB simulations of BER vs. SNR for LDPC-coded 64-QAM under AWGN and Student's t-distributed noise. LDPC codes stay robust under Gaussian noise but need higher SNR in non-Gaussian environments.
The tools I use, grouped by band.
Notes on signals, communication systems, and building AI software.
Lessons from assigning ODUs to multi-carrier transponder framers with six different optimization methods, from exact ILP to swarm algorithms.
What happens to an LDPC-coded 64-QAM link when the noise has heavy tails instead of following the textbook AWGN model.
How our ACM NanoCom 2026 paper treats a plant as a transmitter and stress detection as a receiver design problem, and why that framing works.
Open to conversations about AI software, signal processing, and communication systems, in industry or research.
Cologno Monzese (MI), Italy