I am a Computer Science graduate and Data Scientist with a strong foundation in Python, SQL, statistical modeling, machine learning, MLOps, and big data systems.
I have hands-on experience developing, evaluating, and deploying machine learning solutions. My work includes reproducible preprocessing workflows, distributed inference pipelines, model lifecycle tracking, REST API development, and containerized services.
My thesis research focused on spatio-temporal forecasting for maritime traffic trajectory prediction using AIS geospatial data. I designed temporal features, evaluated deep learning models against baselines and LSTM approaches, and optimized data processing and inference workflows for multi-gigabyte datasets.
I have also built applied AI projects involving retrieval-augmented generation, medical knowledge retrieval, patient risk prediction, transaction anomaly detection, and explainable AI. I use tools such as LangChain, FAISS, OpenAI API, FastAPI, Docker, Streamlit, XGBoost, and SHAP to create practical data products.
My analytical interests include business intelligence, customer analytics, temporal data mining, anomaly detection, model calibration, feature engineering, and human-in-the-loop decision support. I am open to relocation within Europe.
