Senior Data Scientist (Quantitative Finance & ML)

1.

Time-Series Forecasting: Design and implement advanced machine learning models (e.g., LSTM, GRU, Transformers, or XGBoost) specifically optimized for non-stationary time-series data and stock price forecasting.

2.

End-to-End Pipeline Development: Build and maintain robust data pipelines for ingesting high-frequency market data, alternative data (sentiment, news), and fundamental indicators.

3.

Advanced Feature Engineering: Develop sophisticated features including technical indicators (RSI, MACD), volatility measures, and market microstructure signals to improve model alpha.

4.

Exploratory Data Analysis (EDA): Conduct deep-dive analysis to identify patterns, seasonalities, and anomalies in historical market data while accounting for "look-ahead" bias.

5.

Data Cleaning & Normalization: Handle complex data issues such as missing values, stock splits, dividends, and outliers that frequently corrupt financial datasets.

6.

Backtesting Frameworks: Create rigorous backtesting environments to evaluate model performance, ensuring results are statistically significant and account for transaction costs and slippage.

7.

Model Validation & Testing: Implement Walk-Forward Optimization and Cross-Validation techniques tailored for temporal data to prevent overfitting.

8.

Risk Management Integration: Incorporate risk metrics (Sharpe Ratio, Maximum Drawdown, Value at Risk) into the model evaluation process to ensure capital preservation.

9.

Deployment & Monitoring: Deploy models into production environments and set up real-time monitoring to detect "model drift" as market regimes change.

10.

Stakeholder Communication: Translate complex algorithmic results into actionable insights for portfolio managers and executives, bridging the gap between data science and finance.