Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am an AI/ML engineer focused on delivering production-grade ML systems for financial crime surveillance and retail analytics. With 3+ years of hands-on experience, I translate complex data into actionable risk signals and revenue improvements, deploying end-to-end solutions that balance regulatory needs with business impact. I thrive in collaborative environments where ML outcomes are translated into clear, actionable insights for stakeholders and investigators. I enjoy building robust data products using Docker, MLflow, and Airflow, integrating outputs into enterprise platforms, and continuously monitoring model performance. My work blends supervised learning, anomaly detection, graph analytics, and feature engineering to uncover hidden patterns, while maintaining strong alignment with business objectives and compliance requirements.…I am an AI/ML engineer focused on delivering production-grade ML systems for financial crime surveillance and retail analytics. With 3+ years of hands-on experience, I translate complex data into actionable risk signals and revenue improvements, deploying end-to-end solutions that balance regulatory needs with business impact. I thrive in collaborative environments where ML outcomes are translated into clear, actionable insights for stakeholders and investigators. I enjoy building robust data products using Docker, MLflow, and Airflow, integrating outputs into enterprise platforms, and continuously monitoring model performance. My work blends supervised learning, anomaly detection, graph analytics, and feature engineering to uncover hidden patterns, while maintaining strong alignment with business objectives and compliance requirements.

Pradeep Ganapathiraju





I am an AI/ML engineer focused on delivering production-grade ML systems for financial crime surveillance and retail analytics. With 3+ years of hands-on experience, I translate complex data into actionable risk signals and revenue improvements, deploying end-to-end solutions that balance regulatory needs with business impact. I thrive in collaborative environments where ML outcomes are translated into clear, actionable insights for stakeholders and investigators. I enjoy building robust data products using Docker, MLflow, and Airflow, integrating outputs into enterprise platforms, and continuously monitoring model performance. My work blends supervised learning, anomaly detection, graph analytics, and feature engineering to uncover hidden patterns, while maintaining strong alignment with business objectives and compliance requirements.…I am an AI/ML engineer focused on delivering production-grade ML systems for financial crime surveillance and retail analytics. With 3+ years of hands-on experience, I translate complex data into actionable risk signals and revenue improvements, deploying end-to-end solutions that balance regulatory needs with business impact. I thrive in collaborative environments where ML outcomes are translated into clear, actionable insights for stakeholders and investigators. I enjoy building robust data products using Docker, MLflow, and Airflow, integrating outputs into enterprise platforms, and continuously monitoring model performance. My work blends supervised learning, anomaly detection, graph analytics, and feature engineering to uncover hidden patterns, while maintaining strong alignment with business objectives and compliance requirements.

Available to hire

I am an AI/ML engineer focused on delivering production-grade ML systems for financial crime surveillance and retail analytics. With 3+ years of hands-on experience, I translate complex data into actionable risk signals and revenue improvements, deploying end-to-end solutions that balance regulatory needs with business impact. I thrive in collaborative environments where ML outcomes are translated into clear, actionable insights for stakeholders and investigators.

I enjoy building robust data products using Docker, MLflow, and Airflow, integrating outputs into enterprise platforms, and continuously monitoring model performance. My work blends supervised learning, anomaly detection, graph analytics, and feature engineering to uncover hidden patterns, while maintaining strong alignment with business objectives and compliance requirements.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Fluent

Work Experience

AI/ML Engineer at JPMorgan Chase

October 1, 2024 - Present

Analyzed historical AML alert datasets using Python, SQL and Pandas to measure alert-to-SAR conversion and false-positive ratios, enabling a 30% reduction in low-value alerts and improved investigator allocation efficiency. Developed ensemble models (XGBoost, LightGBM, Random Forest) to generate probability-based risk scores, increasing high-risk alert prioritization accuracy by ~25% and improving SAR targeting outcomes. Enhanced detection of hidden laundering patterns with Isolation Forest, DBSCAN and autoencoders, uncovering additional suspicious behaviors and strengthening early detection of emerging typologies. Engineered behavioral, graph, and temporal risk indicators using tsfresh, NetworkX and Neo4j, enabling identification of multi-hop layering and mule networks, contributing to ~20% improvement in detection coverage. Containerized and deployed models using Docker, MLflow and Airflow, integrated risk scores into Actimize, and monitored drift via Power BI and Grafana, supporting

AI/ML Engineer at Deloitte – India

January 1, 2021 - August 1, 2023

Analyzed historical sales, pricing and promotion data to identify regional/category demand patterns and enable data-driven pricing decisions, improving forecast accuracy by ~12%. Built price-elasticity and promotion-uplift models using Regression, Elastic Net and GBM, helping optimize discount depth and drive promo-driven revenue uplift by 3–7% across key categories. Engineered competitive and behavioral pricing features with Pandas and NumPy, improving model accuracy and contributing to a ~10% increase in margin optimization efficiency during seasonal promotions. Conducted scenario simulations and price testing (A/B and location-based) to evaluate volume, revenue and margin trade-offs, supporting pricing decisions that reduced over-discounting by ~15%. Automated pricing insights through Power BI dashboards & Airflow pipelines, improving reporting frequency from monthly to weekly and reducing pricing decision turnaround time by ~30%.