I’m an ML Engineer focused on financial machine learning and quantitative systems. I build models and pipelines that analyze financial markets, extract signals from noisy time-series data, and support decision-making in trading and risk systems.
My work sits at the intersection of machine learning, statistics, and quantitative finance. I focus on transforming raw market data into structured, interpretable signals using probabilistic models, feature engineering, and robust evaluation frameworks.
I’m especially interested in market microstructure, time-series modeling, Kalman filtering, signal classification, and building data-driven trading systems that are both statistically sound and production-ready.
I approach financial ML with a strong emphasis on realism: avoiding overfitting, handling non-stationarity, validating strategies through proper backtesting, and ensuring robustness across different market regimes.
| Area | Tools & Technologies |
|---|---|
| Programming & Scripting |    |
| Operating Systems |   |
| Cloud Platforms |  |
| Big Data & Analytics |   |
| Containers & Deployment |  |
| Machine Learning |    |
| Financial ML & Modeling | Time Series Analysis · Kalman Filtering · Statistical Modeling · Signal Processing · Regression Models · Classification Models |
| Quantitative Methods | Statistical Inference · Hypothesis Testing · Volatility Modeling · Backtesting · Risk Metrics (Sharpe, Drawdown) |
| Feature Engineering | Technical Indicators · Rolling Statistics · Lag Features · Market Microstructure Features |
| MLOps & Infrastructure | MLflow · CI/CD pipelines · Model versioning · Experiment tracking |
| Explainable AI (XAI) | SHAP · Feature Importance · Model interpretability · Signal explainability |
- Market Signal Modeling — extracting meaningful signals from noisy financial time-series data
- Quantitative Feature Engineering — designing statistically valid features
- Kalman Filtering Systems — adaptive smoothing for latent price estimation
- Backtesting & Validation — testing strategies under realistic market conditions
- Risk-Aware Modeling — evaluating models using financial metrics (Sharpe, drawdown, etc.)
- Production ML Systems — building scalable pipelines for financial prediction systems
[Kalman Filter · Time Series · Signal Classification]
Built a financial ML system using Kalman filtering to reduce market noise and extract latent price trends from time-series data.
[XGBoost · Feature Engineering · Market Data]
Classifies trading signals into good / medium / bad using engineered market features.
[MLflow · Docker · GCP]
End-to-end ML pipeline with experiment tracking, containerization, and cloud-ready deployment.
I’m open to opportunities in quantitative machine learning, financial ML engineering, and algorithmic trading systems.
