Contact information

You can get this candidate's contact information from https://www.work.ua/resumes/20231501/

Work experience

Data Scientist / ML Engineer

from 07.2025 to 07.2026 (1 year)
AnalyticsVisio, Львів (IT)

Architected end-to-end ML delivery for 3,000+ assets and 12M price bars: data ingestion, feature engineering (top 20 of 60 features), training and monitoring dashboards.
Deployed 3/7/14-day price-direction models to production as Dockerised FastAPI services with weekly Airflow retraining, combining a regime classifier, ensemble and quantile regression.
Spearheaded nine pre-registered walk-forward studies that traced a backtest Sharpe ratio of ~10 to data bugs (true value 0.40), saving the company from a false trading edge.
Initiated a data audit that uncovered 63 ticker collisions corrupting over half of the profitable-looking trades, then fixed them with deduplication and liquidity filters.
Engineered a meta-model that predicts when the main model fails; ablation showed the largest filter cut risk-adjusted return by 23%.
Consolidated 2.27M news items into 1.17M stories with sentence embeddings and clustering, run as daily Airflow jobs behind FastAPI.

Education

Київський політехнічний інститут імені Ігоря Сікорського

Факультет програмних систем та прикладної математики, Прикладна математика, Київ
Unfinished higher, from 2023 to 2027 (4 years)

Knowledge and skills

• Цілеспрямованість
• Python
• Nympy
• EDA
• Matplotlib
• Pandas
• Seaborn
• SQL
• Apache Airflow
• FastAPI
• Docker
• MS Excel
• Tableau
• Scikit-learn
• Anthropic claude
• Github copilot
• XGBoost
• Quantile Regression
• Ensembles
• Probability Calibration
• Time Series
• Anomaly Detection
• Text Classification
• Clustering
• Pre-Registered Criteria
• Leakage Detection
• Custom Skills
• Multi-Agent Code Review
• LLM API
• PyTorch

Language proficiencies

English — above average