Hi, I'm Péter Gyarmati

Péter Ferenc Gyarmati
🇦🇪 Abu Dhabi, UAE | 🇦🇹 Vienna, Austria

I translate interesting problems into well-engineered systems. This approach, informed by my Computer Science background from the University of Vienna , has shaped my work across a range of commercial and public-sector challenges. I’ve had the chance to architect systems that turn raw vehicle telemetry into intuitive platforms for Magna , and develop geospatial frameworks that help public institutions like the City of Vienna and Austrian Bundesministerium to comply with regulations and make data-informed policy decisions. Internally, I’ve led strategic initiatives such as a company-wide tech transition from Node.js to Python at STOIC , navigating the challenges of a fast-paced startup environment.

This focus on system-building now drives my work at the frontier of agentic AI and visual data analysis. While finishing my Master’s in Data Science at the University of Vienna with my advisors Torsten Möller, Laura Koesten, and Dominik Moritz, I’m exploring how we can use generative models for data analysis, visualization recommendation, and automated chart critique, building on my contributions to systems like Draco 2 and other open-source libraries.

This blend of research and practical engineering is central to my current visiting role at MBZUAI in Abu Dhabi. Collaborating with the Human-Computer Interaction department, I design AI systems that assist in visual data analysis that are not only powerful, but also intuitive, explainable, and sustainable. My approach involves developing a hybrid framework that integrates generative techniques with deterministic methods, driven by the principle that even exploratory work benefits from a thoughtful approach to engineering.

Featured Projects

Agentic Visual Reporting

Agentic Visual Reporting

An agentic system addressing the trade-off between speed and reliability in data analysis. By combining AI for creative tasks with deterministic modules for visualization, it generates both explorable reports for readers and verifiable notebooks for analysts. This hybrid approach explores a more transparent and adaptable model for human-AI partnership in generating insights.

AIResearchVisualization+4
Driva

Driva

An exploration into humanizing vehicle telemetry. The project addresses the challenge of translating vast streams of raw automotive data into meaningful, intuitive experiences for drivers, moving beyond mere numbers to provide actionable insights for safer and more efficient mobility.

AnalyticsFull-stackPlatform+5
Draco 2

Draco 2

A flexible constraint-based system that addresses the rigidity of automated visualization tools. By modeling design expertise as a set of logical rules, it helps researchers and practitioners create effective charts without deep design knowledge. Its core innovation is a renderer-agnostic format, democratizing visualization by making expert knowledge computational and extensible.

AIResearchVisualization+2

Timeline

September 15, 2025

Arrived in Abu Dhabi to begin my visiting role at MBZUAI .

September 14, 2025

My work on an agentic system for visual reporting was invited for presentation at the VISxGenAI Workshop at IEEE VIS 2025.

June 24, 2025

My research on the alignment of human and AI perception in visualization was accepted for presentation at IEEE VIS 2025.

May 20, 2025

Began a freelance engagement with a leading US AI lab, focused on enhancing the agentic software engineering capabilities of their models.

February 11, 2025

Invited for a visiting role at the Human-Computer Interaction department of MBZUAI in Abu Dhabi. My work will focus on an AI system for providing principled, context-aware feedback on visualization design.

February 1, 2025

Made the difficult decision to leave STOIC after recognizing a divergence in our long-term vision. I remain grateful for the support and understanding my colleagues have shown during this transition.

December 18, 2024

Received the Best of the Best award from the University of Vienna for outstanding academic performance and shared my experiences in an accompanying interview.

October 21, 2024

Showcased STOIC ’s AI-powered portfolio management system to investors and stakeholders at the London Stock Exchange .

June 10, 2024

Presented the redesigned STOIC platform to investors in London, demonstrating an experimental hybrid system for eliminating hallucinations in data-driven LLM outputs. Promoted to VP of Engineering the same week.

January 1, 2024

Initiated the migration of the STOIC platform from Node.js to Python on top of AWS to better support the integration of large-scale AI and ML workflows.

October 25, 2023

Presented our short paper on Draco 2 at IEEE VIS 2023 in Melbourne, Australia, and spent a week engaging with the international visualization community.

October 15, 2023

The PLUTO platform was officially launched at the World Health Summit in Berlin.

October 1, 2023

To align my studies with my professional focus, I transitioned to the Master’s in Data Science program at the University of Vienna , concentrating on AI, ML, and data visualization in a Human-Computer Interaction context.

September 27, 2023

Presented our Draco 2 research on automating visualization recommendation with Answer Set Programming at the University of Potsdam .

August 26, 2023

Married after seven years together.

July 3, 2023

Assumed the role of Lead Developer at STOIC , contributing to the development of an Intelligent Data Cloud that augments human intelligence with generative AI, machine learning, and symbolic logic.

April 21, 2023

Delivered a technical talk on code generation and metaprogramming in Dart at the FlutterVienna meetup.

March 22, 2023

Won the hackathon at the FlutterVienna meetup, receiving tickets to the WeAreDevelopers World Congress in Berlin.

March 1, 2023

Began my Master’s in Computer Science at the University of Vienna .

December 18, 2022

Began a collaboration with the Political Science Department at the University of Vienna to build a digital platform for their Public VaLUe Assessment TOol (PLUTO), a framework for data solidarity published in The Lancet.

December 1, 2022

Graduated with a Bachelor’s in Computer Science from the University of Vienna with distinction.

October 1, 2022

Awarded the Merit Scholarship from the University of Vienna , ranking first in the Computer Science program with a perfect 1.0/1.0 ECTS average for the academic year.

July 28, 2022

Contributed to the Draco visualization project to support an integration for my BSc thesis project. This led to an invitation from @domoritz to join the Draco 2 research collaboration, beginning a weekly exchange with researchers from University of Washington , University of Maryland , and Carnegie Mellon University .

June 1, 2022

Transitioned to a full-time, full-stack developer role at LEAN-FORGE while completing my Computer Science degree.

June 1, 2021

To deepen my expertise in frontend development, I joined LEAN-FORGE as a Mobile and Web Developer, working with Flutter and Next.js . This role was undertaken in parallel with my work at TU Wien EEG and my studies.

October 15, 2020

Joined the Energy Economics Research Group at TU Wien as a System Administrator & Backend Developer, where I worked on geospatial analytics, developed full-stack platforms for energy system modeling and maintained bare-metal servers hosting long-running simulations and confidential datasets.

September 1, 2019

Relocated to Vienna to begin my Bachelor’s in Computer Science at the University of Vienna .

July 4, 2019

Graduated from the IB Diploma Programme with a score of 42/45, setting a new school record at the time and achieving its first 7 in Higher Level Mathematics.

May 10, 2019

My Java project for learning graph algorithms received a special commendation and the Talent Passport in the national finals of the 28th Youth Scientific and Innovation Talent Search Competition. This recognition led to an invitation to the Hungarian Innovation Grand Prix at Parliament.

April 26, 2019

As a team of two, we advanced to the finals of the Thyssenkrupp Coding Tomorrow Cup, competing alongside senior programmers and MSc student teams.

January 29, 2019

My project on the interactive visualization of graph algorithms was selected for the national finals of the 28th Youth Scientific and Innovation Talent Search Competition. This included the opportunity for mentorship with physicist Norbert Kroó at the Institute for Particle and Nuclear Physics.

November 5, 2018

To make complex graph algorithms more accessible, I developed a framework in Java for their interactive learning and visualization, which was submitted to the 28th Youth Scientific and Innovation Talent Search Competition.

October 30, 2018

Achieved first place in the opening round of Ericsson ’s programming championship by adapting Dijkstra’s algorithm to solve a pathfinding problem in a competitive simulation.

May 15, 2017

Awarded a full scholarship to the IB Diploma Programme, specializing in Higher Level Mathematics, Computer Science, and German.

April 3, 2017

Joined Ripassa as a Software Developer to build automations and integrations in Python and backend services with Java .

April 1, 2016

Wrote my first line of code with Swift Playgrounds. Having previously studied several human languages, I found a similar and compelling structure in programming, shifting my focus to this new form of problem-solving.

January 18, 2016

After a 12-year journey in competitive basketball, culminating in several medals in national youth championships, I decided to redirect my focus toward academic and technical challenges.