AI researcher · builder · fourth-year student at AGH

I study how intelligent systems make decisions - and build the ones that remove real work.

I turn real problems into models and systems that make people’s work simpler. I combine research with implementation - and test whether the result genuinely helps.

Data science
Machine learning
Medtech
Fintech
Automation

See my work ↓Research / papers ↗

Talk about a problem ↗

01 / ResearchBest Paper AwardPP-RAI 2026 ↗02 / ProductProceroLive system ↗03 / LeadershipPresidentAGH Quant Finance ↗

04 / EducationComputer Science & ISAGH University of Krakow

Selected work

Two systems I took beyond the idea.

Procero began with an operational bottleneck. BloodAI began at a hackathon and developed into an awarded research paper. Both taught me to connect a model with a real workflow.

01Medical AI · Hackathon2025-2026

Hackathon prototype → Best Paper Award

BloodAI

A medical triage prototype that became a published research project.

Built during the Anthropic × Cerebral Valley hackathon, BloodAI routes cases from basic laboratory parameters and an adaptive interview. Together with Jan Banasik, I developed the idea into a multi-label BERT paper awarded Best Paper at PP-RAI 2026.

Paper details ↗AGH announcement ↗Project video ↗

Reported held-out validation

ROC AUC / 8 routes

Primary care0.98

Gastro0.92

Haematology0.94

Nephrology0.95

Emergency1.00

Cardiology0.89

Pulmonology0.75

Hepatology0.91

325,829train + validation encounters

8independent care routes

2MIMIC + Synthea data sources

Research prototype for clinician decision support - not a diagnostic system.

02Retail optimisation · ProductLive

Built for a real purchasing workflow

Procero

One place for purchasing, supplier comparison, and inventory decisions.

I built Procero for small and medium grocery chains. It brings sales, inventory, and wholesaler price lists together to recommend what to order, when, and from whom - without managers manually comparing dozens of files.

Visit Procero ↗Open demo ↗

PROCERO / CASE STUDY9-store grocery network

Time to prepare an order

2 h→8 min

Annual purchasing≈ PLN 50M

Reported price savings3-4%

Wholesalers compared18

Estimated annual value≈ PLN 1.5M

Figures reported in Procero’s published customer case study.

In progress

What I’m working on now.

Agents / RAG

Knowledge and workflow agents for the window industry

A current industry project connecting domain knowledge with agent workflows. Details and evaluation will be published when the system is ready to show.

Quant / Causal modelling

Information Diffusion Dynamics Network

A research concept asking whether the path and topology through which information reaches market participants causally affects price dynamics - independently of content.

How I can help

For teams that know where work hurts - but not yet what to automate.

I work best with non-technical founders and companies that want a practical route from a manual process to a tested AI-enabled workflow.

Agent workflows and RAG

I connect language models to company knowledge, tools, and existing processes - then evaluate whether the workflow is actually reliable enough to use.

Workflow map · working prototype · evaluation

Process automation

I look for repetitive decisions and manual hand-offs that can be removed with software, data, or an agent - not AI for its own sake.

Process review · automation · integration

Applied AI research

I turn a technical question into experiments, compare credible methods, and document what works, what fails, and what the evidence supports.

Research review · experiments · recommendation

About

I’m Antek. I like learning hard things and making other people’s work easier.

I’m a fourth-year Computer Science and Intelligent Systems student at AGH University of Krakow. I want to grow into an AI researcher who can move comfortably between mathematics, code, and the reality of a business process.

I’m naturally interdisciplinary. Medical NLP taught me to think about safety and validation. Causal inference made me more careful about conclusions drawn from data. Procero taught me that a technically interesting system still has to fit the way people actually work.

Outside the projects themselves, I enjoy hackathons, networking, and connecting people who should know each other. I volunteer in educational initiatives and serve as President of AGH Quant Finance. I try to work hard, think clearly, and leave a process better than I found it.

GitHub ↗LinkedIn ↗Research log ↗Email ↗

CV snapshot

Experience, education, and leadership.

A quick overview for research and engineering teams. I’m especially interested in AI research, data science, and applied AI roles where experiments meet real systems.

Experience & leadership

Current

Data Science & ML - Search

E-commerce

Working with search queries, relevance data, process automation, and operational optimisation.

Current

Co-founder

Procero

Building an operational intelligence product for grocery purchasing and inventory decisions.

↗

Current

Domain Group Lead

Athletic Intelligence

Leading algorithm work for football clubs.

Former AI Researcher

AI Lab, AGH

Student research in artificial intelligence.

Leadership

President

AGH Quant Finance

Leading a student community around quantitative research and finance.

↗

Recognition

Selected, not exhaustive.

2026Best Paper Award

7th Polish Conference on Artificial Intelligence · BloodAI

↗

2026Global Top 500 participant

Anthropic × Cerebral Valley Opus 4.7 AI Hackathon

2025Finalist

First edition of Shark Tank Tech-On Kraków · BloodAI

Contact

Based in Kraków · working remotely

Tell me which part of your work is still unnecessarily manual.

antonipaterbusiness@gmail.com ↗

I’m open to applied AI projects, research collaborations, and conversations with people building something useful.