At Boo Vision, I built end-to-end Graph Neural Network solutions for RF signal processing and radar image classification. I processed multi-terabyte RF datasets and developed edge-aware models that matched CNN-level classification performance while reducing model complexity by several orders of magnitude.
At the Institute for informatics and automation problems of NAS RA, I researched Graph Neural Networks, graph representation learning, and explainable AI for computer vision. On Upwork, I developed and backtested quantitative trading strategies and predictive models; at Deeptech GigaHack 2026, I helped develop a computer vision prototype for vineyard analysis using aerial drone imagery.

