Building deployed ML & RAG projects | Seeking 2026 Data/ML/SWE Internship
I am a Bioinformatics student at Poznan University of Technology focused on machine learning and data application development. I learn by building complete projects and deploying them as working applications. I am actively seeking a data, machine learning, or software engineering internship for 2026/2027. I am open to opportunities in Poland and remote across the EU.
- 🧬 Education: B.Sc. in Bioinformatics, Poznan University of Technology (Expected Apr 2028).
- 🏆 Certifications: NVIDIA DLI - Fundamentals of Deep Learning (2025); Kaggle - Advanced SQL, Intermediate ML, Time Series (2026).
- 🧠 Experience: Member of the Data Science Section at GHOST Student Scientific Circle and KNBI Bioinformatics Student Association.
- 📫 Contact:kyrylo.kudrevych@gmail.com
Languages & Databases
Machine Learning & AI
-EE4C2C?style=for-the-badge&logo=pytorch&logoColor=white){kind=icon}
Data Engineering & Visualization
Frameworks & Tools
👉 View Live Demo | 🔗 View Source Code A rent price estimator for the Poznań market.
- Stack: Python, FastAPI, Streamlit, Scikit-Learn, CatBoost
- Highlights:
- Scrapes rental listings, trains a CatBoost model (validation MAE ~307 PLN), and serves predictions through a FastAPI API.
- Compared several models and chose CatBoost after benchmarking on log-transformed prices.
- Deployed with Railway and set up a simple CI/CD pipeline for automatic updates.
🔗 View Source Code A local RAG application that answers rule disputes based on the official TDA poker rulebook.
- Stack: LangChain, Llama 3, ChromaDB, aiogram
- Highlights:
- Delivered as an async Telegram bot running fully offline via Ollama, with responses perfectly grounded in retrieved rule citations.
- Selected local inference via Ollama over API-based models to keep the system fully offline and free of per-request costs.