Назар

Hnatyshyn Nazar | Data Scientist
23 Sakharoza
[открыть контакты](см. выше в блоке «контактная информация») [открыть контакты](см. выше в блоке «контактная информация»)
Academic Street, Lviv

ABOUT ME
I’m a 4th-year Computer Science student at Lviv Polytechnic, majoring in Computational Intelligence
of Smart Systems. I’m passionate about artificial intelligence and currently developing my skills in data science. I enjoy
learning new things, exploring innovative technologies, and in my free time, I play volleyball and computer games.

TECHNICAL SKILLS ONLINE PROFILES
Languages → Experience: Python, SQL, C#/C++
github.com/MsNazarino
Tech Stack → Activily Used: VSCode, Jupyter Nootebook(Anaconda), Visual [открыть контакты](см. выше в блоке «контактная информация»)
Studio, PyCharm, MSSQL, MySQL
kaggle.com/msnazarino
Familiar: Docker, Git, MongoDB
Business Modeling → Understanding of business logic, workflows, and system LANGUAGES
structure Ukrainian: Native
English: Pre-Intermediate
EDUCATION & CERTIFICATION
SOFT SKILLS
Lviv Polytechnic National University 📍2022 – 2026 (expected) Effective communication
Bachelor’s Degree in Computer Science (Smart Systems and Computational Teamwork
Intelligence) Department of Automated Control Systems Time management
Problem-solving
Cisco Certification CCNAv7: Introduction to Networks (link)

WORK EXPERIENCE
Database Fundamentals (Lviv Polytechnic, 2023)
Completed academic course on relational databases using MSSQL.
Independently developed small projects with MySQLand MongoDB for personal assignments.
Lviv Polytechnic – Information Systems Design
Engineered a information system tailored to business and user specifications, utilizing modeling tools such as
UML, DFD, IDEF0/IDEF3, AllFusion Process Modeler, and ERwin.

PROJECTS
Theories & Methods of Computational Intelligence
Calorie Prediction: Linear Regression, Decision Tree, Random Forest, Ensemble methods. Developed and compared
models using Grid Search for hyperparameter optimization to ensure the highest predictive accuracy.
Data Clustering: K-Means, DBSCAN, PCA. Uncovered hidden patterns by developing and comparing clustering models
with PCA dimensionality reduction for optimized data visualization and improved model performance.
Fuzzy Logic Control: NumPy, scikit-fuzzy, Matplotlib. Implemented Mamdani inference system with linguistic variables
and membership functions to simulate human-like decision-making and visualize outputs through defuzzification.
Perceptron Classifier: PyTorch, NumPy, Scikit-learn, Matplotlib. Developed a binary classification model, implementing
weight optimization and activation functions to visualize decision boundaries and non-linear transformations.
NLP Analysis: NLTK, GloVe, NumPy. Processed text data through tokenization and stop-word removal, generating word
embeddings and utilizing cosine similarity to evaluate semantic relationships between words.
Image Classification: PyTorch, torchvision, ResNet, VGG. Developed a transfer learning system by freezing pre-trained
layers, designing custom classifier heads, and optimizing training using the Adam optimizer.
Neural network technologies and systems
Transformer Text Classifier: PyTorch, BERT Tokenizer, NumPy. Developed a sequence classification model using
Positional Encoding and Transformer layers, achieving 99.6% accuracy via hyperparameter tuning and class balancing
LLM API Integration: LM Studio, OpenAI API. Developed a CLI tool to integrate local LLMs via OpenAI-compatible API.
Implemented system prompts, hyperparameter tuning and automated Markdown dialogue logging
RAG System Development: FAISS, LangChain, PyPDFLoader. Built a RAG pipeline using sentence-transformers for
PDF indexing. Implemented dual-metric vector search and integrated local LLMs via LM Studio
Image Generation: Python, Diffusers, PyTorch. Implemented a Stable Diffusion v1.5 pipeline to generate high-quality
images. Explored prompt engineering, negative prompts, and hyperparameter tuning across diverse artistic styles.
Multimodal VQA: PyTorch, Transformers, LLaVA-1.5-7B, PIL, Hugging Face. Developed an image-to-text system for VQA
tasks, optimizing outputs through temperature and top_p parameter tuning
Agent-Based Assistant: ReAct, Python, ChatOpenAI, LM Studio, ConversationBufferMemory. Developed AI agent with
custom tools for NLP and mathematical tasks, implementing memory and zero-shot reasoning
AI Knowledge Assistant: LangChain, FAISS, PyPDFLoader, ChatOpenAI, ConversationBufferMemory. Developed an
autonomous ReAct agent integrating a PDF-based RAG pipeline with semantic search and text summarization tools
Kaggle - House Prices
Pandas, NumPy, Scikit-learn, XGBoost. Built an end-to-end regression pipeline with EDA, feature engineering,
missing value handling, log-target transformation, model evaluation using RMSLE.