Prajwal Pol

I'm a passionate Quantitative Researcher with 6+ years of experience building high-performance algorithmic trading strategies in the Indian markets.

I've successfully managed over $10M in AUM, developed ML-powered systems that deliver 35%+ annual ROI, and built proprietary models using Python, XGBoost, and live options data feeds.

My expertise spans options Greeks, derivatives pricing, and signal generation using high-frequency data. I thrive on designing systems that convert market noise into logic-driven, profitable decisions.

I'm currently exploring advanced AI-driven trade models and seek to collaborate with research-focused teams in hedge funds, prop trading desks, or fintechs.

Always open to opportunities where I can bring value through data, discipline, and domain knowledge.

• Created a custom Python backtesting engine supporting multi-leg options strategies, theta decay modeling, re-entries, and SL logic.
• Performed extensive backtests across 500+ trading days, validating strategy edge with a Sharpe ratio > 2.0 and max drawdown under 5%.
• Analyzed and optimized option strategy parameters using Grid Search & Bayesian Optimization for robust performance across market regimes.

• Developed a proprietary ML model to predict intraday market direction, achieving ~75% accuracy on real market data, improving trade entry precision.
• Built a rule-based and AI-enhanced option selling system for Nifty, yielding an average 35% annualized ROI with controlled drawdown.
• Integrated real-time OI, IV, and price action data into a directional signal engine, increasing signal quality by 30% vs previous version.
• Trained multiple ML models (XGBoost, LightGBM) on 2 years of 1-minute option chain and spot data to generate highly reliable sell signals.

• Automated real-time data ingestion and feature extraction using Zerodha Kite API, enabling live ML model predictions at 9:18 AM daily.
• Deployed full Python pipeline with logging, real-time strike selection, and signal explanation, reducing manual effort by 90%.
• Created an option-chain merging tool that handled 10M+ rows of CE/PE/Spot data per day, reducing processing time by 75%.

• Managed an algo-driven portfolio with $10M AUM, focusing on intraday index option selling strategies.
• Generated an average of 35% ROI per year over 3+ years with disciplined risk and position sizing.
• Led research initiatives on volatility-based filters and trend-adaptive entries, improving win rate by 20%.