About
A Czech computer scientist who ships production systems and is turning that discipline toward AI safety.
I’m a Czech computer scientist working at the intersection of applied AI and AI safety — shipping production systems as a founder while building, in public, a research track on how oversight of language models breaks. This page is the long version.
I started programming as a teenager and went through the eight-year selective gymnasium track at Gymnázium Mladá Boleslav. I briefly studied pharmaceutical synthesis at VŠCHT before transferring to computer science at the Faculty of Mathematics and Physics, Charles University (MFF UK), where I’m finishing my Bachelor’s degree in 2026.
My early projects were systems-flavoured — a RISC-V operating system kernel with a 3-person team, a custom Bitcoin transaction backtester in C++, an Ant Colony Simulator in Unity exploring emergent intelligence from local rules. The thread connecting them is curiosity about what makes complex behaviour appear from simple components.
That same thread pulled me toward AI safety. Reasoning models “think out loud” in a visible chain of thought, and one of the field’s main hopes is that we can read those thoughts and catch strategic misbehaviour — scheming, deception, sandbagging — before it lands. That hope is fragile, and measuring exactly where it breaks is work that rewards careful engineering more than credentials. That is the bet I’m making.
From October 2026 I’ll be doing my Master’s in Artificial Intelligence at MFF UK. My research theme is multilingual robustness of AI oversight — safety tooling is built and tested overwhelmingly in English, and I study what happens to it in the other several thousand languages:
Native Czech — a mid-resource language where I can do the human verification most labs can’t do in-house — is a deliberate part of the method, not a gimmick.
Alongside the research, I’m co-founder and CTO at Zoplio. We’re building the AI scheduling primitive — a hosted API any application can embed to delegate meeting negotiation. The technical core is an agent runtime: a bilateral negotiation protocol between agents, confidence-scored memory of how a person actually wants to be scheduled, an LLM-driven conversation engine, and integrations for Google Calendar, WhatsApp, and Stripe. We’re backed by BUDETO Studio (€50k pre-seed).
I also co-founded Boletiqo with Lukáš Hellesch — an AI company platform where autonomous agent teams plan, ship, sell, and close. We reached Red Bull Basement ’26 Czech Republic national top 10, and I wound it down in 2026 to focus. Watching our own agents misrepresent intermediate results and produce convincing post-hoc justifications at the edge of their capability was a formative push toward oversight research.
I view the founder side as a useful counterweight to research: it forces me to take AI deployment realities seriously, and it puts me in the room when models actually break.
Continuing at the Faculty of Mathematics and Physics, Charles University. Research theme: multilingual robustness of AI oversight — chain-of-thought monitorability, deception evals, cross-lingual evaluation.
Bachelor’s thesis: Bitcoin Wallet for Advanced Users, supervised by RNDr. Filip Zavoral, Ph.D., defended 18 Jun 2026. Degree completion 2026.
Brief detour at the University of Chemistry and Technology Prague (VŠCHT, 2022–2023, transferred). Selective gymnasium at Gymnázium Mladá Boleslav (maturita 2022).
I keep these two lists separate on purpose: the first is what I’ve shipped and been paid for; the second is the research toolkit I’m acquiring with the project itself, in public.