I build accessible, pixel-perfect interfaces, mostly React + TypeScript. Lately, agentic AI and multi-agent systems.
I build clean, accessible web interfaces. Frontend stuck with me because I like seeing the result of what I build. React and TypeScript, mostly.
I've shipped across the stack, from SaaS to crypto to larger systems. I hold a master's from the University of Maribor, focused on LLMs.
Lately I've been spending a lot of time experimenting with agentic AI and multi-agent orchestration. If I'm not working, I'm probably outside.
Frontend engineer on blockchain platforms. Wallet connectivity, smart contract interactions. TypeScript, React, Angular, Java Spring.
Developed features for the Blocksi platform and website. Vue.js, Elasticsearch, MongoDB, PHP.
Built new features for the company website and EV charging application. Vue.js, Firebase, Docker.
Built a PWA platform with React and MUI. Implemented WebSockets and JWT authentication. Created a React Native prototype.
ML pipeline that predicts Strava activity patterns — whether a user will be active in the next 8 hours and how many kudos an activity will receive. Automated training, evaluation, and daily predictions via GitHub Actions.
Full-stack real estate scraper. Fetches ~500 listings from a Czech property site, stores them in PostgreSQL, and serves them through a React frontend — all containerized with Docker.
Python library that combines SHAP analysis with GPT to generate natural-language explanations of ML model predictions — tailored to different audiences, from beginners to researchers.
Data science project that monitors and predicts availability of the Mbajk bike-sharing service. Includes data pipelines, model training, and API serving.
Open to interesting projects and conversations. Drop a message or reach out on any of the channels →