Available for contract work

Ten working days,
one number
to decide on

The evidence is below: three problems I take on as a contractor, on model work that has to survive a regulatory file and not only a benchmark.

  • Since 2022AI Research Scientist at Laza Medical, a cardiac device company in the Shifamed portfolio, on robotic cardiovascular imaging
  • 3rdFOMO25 method track, MICCAI 2025
  • 800+Citations
01

Problems I solve

Three of them. Each one has published work behind it.

Reconstruction

3D from too few 2D views

Two angiographic planes. A freehand ultrasound sweep. A stack of slices with gaps between them. The volume still has to be anatomically plausible where the acquisition never looked, and that is what a learned shape prior is for.

  • Biplane is all you need (under review)
  • Liver mesh GNN, IEEE ISBI 2023
  • Whole-heart SSM, arXiv:2608.19932

Label efficiency

Models that work when the labels are not there

Self-supervised pretraining, annotation-efficient segmentation, and evaluation on the cohort you actually have rather than the one you wish you had. I report the failures too: modality-invariant pretraining helped on several tasks in our hands and hurt lesion segmentation.

  • SSL-DSE grant, 148,000 EUR
  • Medical Image Analysis, with S. Kadoury
  • FOMO25, 3rd in the method track

Signals

Signals, not just images

Voice and handwriting carry the diagnosis too, and they are cheaper to collect than a scan. Parkinson's disease from voice recordings is my most cited work, at 180 citations.

  • CNN ensemble on voice, 180 citations
  • npj Digital Medicine, speech biomarker
  • IEEE TSMC, offline handwriting

Also a second opinion on a pipeline: where the metric is leaking, and whether the plan holds.

02

The first piece of work

A fixed scope
at a fixed price

Most first conversations do not need a contractor line and a headcount request. They need a result you can act on. So the first piece of work is a fixed scope at a fixed price, both agreed before it starts.

A negative result is a valid outcome and you get it in writing. If the method does not beat your current number, the report says so and we stop there.

Start a scoping engagement

Price quoted after the call, once the scope is agreed.

What is delivered

  • Your metric, reproduced

    On your data, or on a public proxy if the data cannot leave. Which one is agreed before the ten days start.

  • One method tried against it

    One, chosen for your problem. Ten days does not buy a survey.

  • A written report with the number

    The result, how it was measured, and a go or no-go recommendation.

  • A call to walk through it

    So the decision is made with me in the room, not from a PDF.

03

Selected projects

Medical Imaging

Deployed segmentation model

Cardiac valve segmentation from 2D echocardiography

Mitral and aortic valves, found and segmented automatically in 2D echocardiograms. Ultrasound is low in contrast and high in noise, so the U-Net was tuned for that data.

U-Net · Validated with cardiologists · Prototype

LLM / NLP

89.3% accuracy

Bioactive molecules from the literature

An LLM pipeline that reads PubMed papers, finds bioactive substances and their therapeutic effects, and maps each molecule to a disease with entity and relation extraction. It processed 30,000 papers.

30,000 papers · 89.3% extraction accuracy · Checked against ChEMBL and DrugBank

04

Background

Experience

  • Laza MedicalAI Research Scientist

    Robotic cardiovascular imaging at a cardiac device company in the Shifamed portfolio, since December 2022

  • TietoEVRYSoftware Engineer

    Private cloud infrastructure for telecom, 2017 to 2022

  • APELAI Researcher

    LLM for bioactive molecules and disease mapping

  • Cortex VisionResearcher

    Medical imaging diagnostics

Education

  • PhD in Artificial Intelligence

    Technical University of Kosice, 2023

    Visiting PhD, Polytechnique Montréal, 2022

MICCAI 2025

3rd place, FOMO25 Challenge

Foundation Model Challenge for Brain MRI

Awards and funding

  • VAIA research funding, 148,000 EUR2024
  • Best PhD thesis, Technical University of Kosice2022
05
Dr. Matej Gazda speaking at a conference

A researcher who has
shipped inside a device team

I am Matej Gazda. PhD in artificial intelligence from the Technical University of Kosice, a visiting year in Samuel Kadoury's lab at Polytechnique Montréal, and papers in IEEE TSMC, Medical Image Analysis and npj Digital Medicine.

The part that matters to a head of R&D is the other half. Five years of software engineering at TietoEVRY, 2017 to 2022, and since December 2022 AI Research Scientist at Laza Medical, a cardiac device company in the Shifamed portfolio, on robotic cardiovascular imaging. I know what happens to a model between the paper and the clinic.

I work as an external contractor, not as a candidate for a headcount line. The usual first step is the ten day engagement above.

How I work

  1. Call

    Thirty minutes on the problem and the metric you are judged on

  2. Build

    If the engagement is a go, the method goes into your pipeline and your tests

  3. Handover

    Code, weights and the write-up your team needs to keep it running

Research & Collaboration

  • TUKE

    Technical University of Kosice

  • PolyMTL

    Polytechnique Montréal

  • IEEE

  • MICCAI

  • UNLP

    Louis Pasteur Hospital

07

Tell me the metric
you are stuck on

One paragraph is enough: what you are trying to measure, what you get now, and what the data looks like. I answer within a working day and I will say if it is not my problem.

Working together

Based in
Kosice, Slovakia, CET. US East Coast mornings fall in my working afternoon.
Your data
Can stay in your environment, with a public proxy if it cannot leave.
Handover
Code, weights and the write-up are handed over.

Thirty minute call first, at no charge. The engagement is quoted after it.