Ірина

Iryna Popovych
Data Scientist | Machine Learning Engineer
Košice, Slovakia | [відкрити контакти](див. вище в блоці «контактна інформація») | [відкрити контакти](див. вище в блоці «контактна інформація») | [відкрити контакти](див. вище в блоці «контактна інформація») | [відкрити контакти](див. вище в блоці «контактна інформація») | github.com/irapopovych

PROFILE
MSc student in Intelligent Systems with practical experience in Python-based data analysis, supervised and unsupervised ML, feature
engineering, and model evaluation. Developed research pipelines for medical image classification and texture segmentation. Currently
working on an industry-collaborative LLM-based data analysis thesis.
TECHNICAL SKILLS
Programming & data: Python, SQL, pandas, NumPy, SciPy, scikit-learn; EDA, data cleaning, feature engineering
ML & statistics: Classification, regression, clustering; probability, statistical inference, hypothesis testing
Model validation: Train/validation/test splits, cross-validation, performance metrics, overfitting, data leakage
Deep learning & CV: PyTorch, torchvision, OpenCV, MONAI, timm, CNNs, Vision Transformers
Tools & AI systems: Git, Docker, Linux, pytest, Jupyter, Matplotlib, Seaborn, LLM APIs, Knowledge Graphs
SELECTED PROJECTS

Maya Glyph Retrieval with DINOv3 | Research Publication DOI: 10.1007/978-3-032-39028-8_11 2026
Python · DINOv3 · SAM3 · Visual Embeddings · Image Retrieval
• Team research project focused on semi-automated Maya glyph segmentation and similarity-based retrieval using visual embeddings.
• Achieved 88% Top-10 retrieval success (23/26 queries) in a pilot evaluation using binarized images.
Parkinson's Disease Diagnosis via Vision Transformers | BSc Thesis Sep 2024–Jun 2025
Python · PyTorch · MONAI · timm · 3D ViT · TimeSformer · SegFormer3D
• Classified Parkinson's disease from 3D DaTSCAN SPECT images using the PPMI database.
• Implemented and benchmarked 3D ViT, TimeSformer, and SegFormer3D for binary and 3-class supervised classification.
• Best model (3D ViT with SegFormer3D pre-trained weights) achieved F1 = 0.8957 and accuracy = 0.8914.
Unsupervised Texture Segmentation via Classical CV Pipeline 2025
Python · Scikit-learn · KMeans · Gabor Filters · OpenCV
• Built a full unsupervised segmentation pipeline without deep learning: Gabor filter feature extraction, KMeans clustering,
morphological post-processing.
• Applied feature engineering (Gabor filters, local entropy maps) to capture texture complexity and patterns at a local scale.
• Benchmarked on the Prague Texture Segmentation Benchmark; achieved Mean MS score of 49.24.
Knowledge Graph + LLM Data Analysis | MSc Thesis (ongoing) 2026–present
Python · LLM APIs · Knowledge Graphs · AI Evaluation
• Developing an LLM-based system that combines structured knowledge with natural language processing for data analysis.
• Working on information retrieval, query processing, and LLM-based response generation.
• Evaluating system performance, response quality, and reliability through systematic testing.
ParkMe | Team Project in Collaboration with FPT Software 2025–2026
Python · FastAPI · pytest · React Native · SQLAlchemy · Pydantic
• Part of a student team building a real-time parking application for the city of Kosice.
• Covered QA across the full stack: tested FastAPI backend (endpoints, authentication, business logic) and React Native frontend.
• Wrote automated tests using pytest; performed manual testing and maintained test documentation.
CNN Architecture Comparison: Inception-v3 vs. Inception-ResNet-v2 2026
Python · PyTorch · torchvision · Scikit-learn · Matplotlib
• Collaborated in a team to implement and compare two Inception-based architectures on image classification.
• Contributed to model training, evaluation pipeline, and analysis of accuracy, convergence, and compute trade-offs.
EDUCATION
MSc in Intelligent Systems | Technical University of Košice Sep 2025–present
BSc in Intelligent Systems | Technical University of Košice Sep 2022–Jun 2025
Relevant coursework: Machine Learning, Probability & Statistics, Data Analysis, Neural Networks, Computer Vision, Databases
LANGUAGES
English (B2) · Ukrainian (native) · Slovak (B2) · Spanish (A1)