Looking for a job

Venkata Suresh Gunji

@venkatasureshgunji

Machine Learning Engineer at JPMorgan Chase & Co. who built RAG and agentic workflows, cutting investigation time by 28%.

United States

Message

At JPMorgan Chase & Co., I developed anomaly-detection and predictive models for transaction and operational events, achieving 92%+ precision and reducing false alerts by 20%. I also built an LLM-powered knowledge solution and agentic workflows that connected incidents with technical documentation and automated investigation, reducing average analysis time by 28%.

At Honeywell, I developed a prototype operational analytics solution that reduced manual analysis time by 25%. Previously at SAP, I built forecasting and prediction models that improved forecast accuracy by 15%, and I created an enterprise analytics agent and a reusable ML experimentation framework as projects.

Experience

Work history, roles, and key accomplishments

Current

Machine Learning Engineer – Associate

Current

JPMorgan Chase & Co.

Mar 2026 - Present (8 months)

Developed ML solutions for fintech and enterprise operations, analyzing 2M+ transaction and operational events to identify anomalies and service-impacting issues. Built anomaly-detection and predictive models achieving 92%+ precision and reducing false alerts by 20%.

Artificial Intelligence Engineer Intern

Honeywell

Jun 2025 - Nov 2025 (5 months)

Analyzed 1M+ industrial and enterprise operational records using Python, SQL, Pandas, and NumPy to identify abnormal process behavior and operational trends. Engineered time-series and statistical features, applying XGBoost, Random Forest, clustering, and anomaly-detection techniques to improve predictive performance by 18%.

Python SQL Pandas NumPy XGBoost Random Forest Clustering Anomaly Detection Time series Forecasting Feature Engineering Data Analysis

Machine Learning Engineer

SAP

Sep 2021 - Jul 2023 (1 year 10 months)

Built machine learning solutions on SAP enterprise data to improve demand forecasting, business-process prediction, and operational planning across 2M+ transactional and time-series records. Developed classification, regression, and forecasting models using XGBoost, Random Forest, Gradient Boosting, and Logistic Regression, improving predictive performance by 20%+.

Python SQL Pandas NumPy scikit learn XGBoost Random Forest Gradient Boosting Logistic Regression Feature Engineering Model Evaluation Hyperparameter Tuning Cross Validation CI CD Git Jupyter

Machine Learning Intern

SAP

Mar 2021 - Aug 2021 (5 months)

Collected, cleaned, and prepared SAP enterprise datasets using Python, Pandas, NumPy, and SQL for machine learning analysis. Developed scikit-learn models for business-process prediction and classification, and evaluated models using accuracy, Precision, Recall, F1-score, and RMSE.

Python SQL Pandas NumPy scikit learn data preprocessing Feature Engineering Model Evaluation