Quantitative Researcher & ML Engineer | Applied Statistics, Time Series, and Markets
LinkedIn • Email • TradingView
I work at the intersection of quantitative research, machine learning, and software engineering, with a strong focus on financial time series, statistical modeling, and decision-making under uncertainty.
My background is in building and experimenting with models for market behavior, portfolio optimization, risk estimation, and signal research. I enjoy starting from raw data, forming hypotheses, designing experiments, and iterating on models until they either fail clearly or reveal something useful.
I place a strong emphasis on understanding why a model works or breaks, rather than optimizing blindly. Most of my work involves Python-based research pipelines, statistical analysis, feature engineering, and translating research insights into reliable systems.
I am particularly interested in quantitative trading, market microstructure, regime detection, and the application of statistical and ML techniques to real-world financial problems.
Quantitative research platform for portfolio construction and allocation.
- Market data analysis and feature engineering
- Regime-aware optimization strategies
- Backtesting and performance evaluation
- Research pipelines connected to interactive dashboards
Stack: Python, pandas, NumPy, scikit-learn, FastAPI, Docker
Event-driven decision system combining statistical models and rule-based logic.
- Probabilistic scoring and risk assessment
- Model-driven decision workflows
- Emphasis on interpretability and auditability
Stack: Python, .NET, MongoDB, RabbitMQ
Collection of exploratory research on market behavior.
- Time-series analysis and signal exploration
- Pattern detection and regime modeling
- Statistical validation and model comparison
Stack: Python, pandas, NumPy, TA-Lib
- Quant & Data: time-series analysis, statistical modeling, backtesting, regime detection
- ML: supervised models, feature engineering, validation, error analysis
- Programming: Python (primary), C#
- Data: pandas, NumPy, scikit-learn
- Systems: research pipelines, event-driven architectures