Conduct quantitative research focused on systematic trading strategies, execution modelling, and market microstructure analysis across global markets. Design, backtest, and evaluate alpha signals using statistical modelling, time-series analysis, and reinforcement learning approaches. Develop research pipelines and trading simulations in Python & C++, emphasizing robust data handling, realistic execution assumptions, and performance analysis. Collaborate with trading systems team to prepare research strategies for deployment, including validation, parameter robustness, and infrastructure alignment. Work within a research driven environment focusing on disciplined experimentation, risk-aware modelling, and scalable quantitative workflows.

Engineered a high-performance, real-time brand logo identification system using a YOLOv8 object detection pipeline, achieving 95% accuracy and providing critical data for market analysis. Key Contributions: 🔹 Developed and launched an interactive Streamlit dashboard equipped with confidence-scoring algorithms. This tool enabled stakeholders to perform advertisement exposure analytics and directly measure campaign ROI. 🔹 Devised and implemented a scalable framework to calculate logo display percentages across more than 50 distinct marketing campaigns, establishing a foundational system for benchmarking campaign performance.

Spearheaded the development of a customer segmentation model using k-means clustering and Principal Component Analysis (PCA). This model directly improved the targeting of marketing campaigns by 25%, leading to more effective outreach. Key Contributions: 🔹 Executed a comprehensive data preprocessing pipeline that enhanced model stability by reducing input noise by 15%. 🔹 Led sprint-based analytics delivery within a 5-member quantitative team, consistently maintaining 100% adherence to rigorous data quality standards and ensuring the reliability of our insights.