Nikodim Svetlichnyi

Built ensemble ML models (XGBoost/CatBoost/LightGBM) with learned weight optimization and threshold tuning, achieving F1=0.86 and ROC-AUC=0.91 on 118K imbalanced samples; designed custom loss and validated with MCC=0.73. Engineered a 3-stage feature pipeline to reduce inference time 2.8x and applied Bayesian optimization (Optuna, 200 trials) to improve F1 by 3.29% versus grid search.

Developed LSTM time-series models and autoencoders for anomaly detection, achieving MAE=13.1 and 87% recall with 4.2% FPR; implemented hybrid clustering and designed A/B tests with power analysis that detected a 7.3% lift (p=0.002).

Trained and compared regression models using GridSearchCV and 5-fold CV; selected Ridge (alpha=0.5) achieving R²=0.70 and MAE=2.3 while reducing features from 17 to 8 via coefficient analysis.

Drove project delivery to pre-release by aligning scope, defining milestones, coordinating cross-functional execution, and owning product documentation to support release decisions and go-to-market preparation.

Provided analytical support including research, benchmarking, and KPI reporting; standardized evaluation criteria and tracking to reduce turnaround time and maintain data consistency across materials.

Supported project analytics during internship by preparing structured summaries, lightweight reporting, and contributing to pipeline/process improvements to enhance efficiency.

Grade: 7.83 ! ACCELERATED 1-YEAR TRACK, FULL 2-YEAR CURRICULUM !

Activities and societies: Master program on Artificial Intelligence, Robotics & Autonomous Systems; Master Thesis: Robustness in Reinforcement Learning under Task-Uncertainty.

Completed an accelerated M.Sc. in Intelligent Interactive Systems covering AI, robotics and autonomous systems with a thesis on robustness in reinforcement learning under task uncertainty.

Grade: 7.62

Activities and societies: Sailing Club Hermes; Bachelor thesis: Product Category Analysis and Optimization for the Lenta Online Store.

Completed a Bachelor of Economics with strong quantitative training in mathematics, statistics and econometrics and applied data analysis in Python; bachelor thesis on product category analysis and optimization.

Activities and societies: Practical training in AI fundamentals, hands-on Python exercises and practical case analyses.

Completed a short course on Deep Learning & Neural Networks covering practical machine learning and deep learning fundamentals with Python.