Satish Mudrakola
Norwalk,CT
Summary
Data Scientist and Machine Learning Engineer with expertise in developing machine learning pipelines and predictive analytics. Proficient in Python and tools such as Scikit-learn, XGBoost, and Flask for deployment. Experienced in data preprocessing, feature engineering, and model evaluation, delivering actionable insights through interactive visualizations. Focused on leveraging data to drive business outcomes effectively.
Overview
3
3
years of professional experience
1
1
Certification
Work History
SOFTWARE ASSOCIATE
ZUVA ENGINEERING PVT.LTD
12.2020 - 04.2024
- Developed and maintained RESTful APIs using Django and Python, reducing average response time by 25% and improving scalability.
- Automated recurring data processing tasks with Python scripts, saving the team 10 hours per week of manual work.
- Engineered an internal reporting tool with Python and Pandas, increasing data accuracy and cutting report generation time by 40%.
- Collaborated cross-functionally to load data into AWS Cloud Cassandra using Python scripts, supporting seamless data integration.
- Led the migration of a legacy application to Flask, modernizing the tech stack and increasing system reliability.
- Built visualization dashboards for over 40 datasets using Matplotlib and Seaborn, enhancing business insights and decision-making.
- Implemented a custom ETL pipeline with Python, improving data quality by 30% for analytics teams.
- Wrote unit and integration tests with PyTest, ensuring code robustness and reducing bugs for mission-critical features.
- Worked in Agile teams to deliver new features and bug fixes, contributing to 4+ project releases per year.
- Developed and deployed scalable services on AWS Elastic Beanstalk, improving uptime and accelerating deployment cycles.
Education
Master of Science - Computer And Information Sciences
Sacred Heart University
Fairfield, Connecticut, CT05.2026
Skills
- Programming languages: Python
- Machine learning frameworks: Scikit-learn, XGBoost, LightGBM, CatBoost, Random Forest, Logistic Regression, Gradient Boosting, KMeans
- Data analysis tools: Pandas, NumPy
- Visualization tools: Matplotlib, Seaborn, Folium, Streamlit
- Web frameworks: Flask
- Model evaluation metrics: SHAP, SMOTE, ROC-AUC, Precision-Recall, R², RMSE
- Development technologies: HTML, CSS
Certification
Successfully completed. Kaggle’s Intro to Machine Learning program, focusing on core algorithms, feature selection, and performance optimization techniques.
Areas of Expertise
- Data Cleaning, Preprocessing, and Feature Engineering
- Exploratory Data Analysis (EDA) and Statistical Insight Generation
- Predictive Modeling (Classification and Regression)
- Ensemble Learning and Hyperparameter Tuning
- Handling Class Imbalance and Cost-sensitive Learning
- Model Explainability and Interpretability (SHAP)
- Clustering and Hotspot Detection (KMeans)
- Geo-spatial and Temporal Data Analysis
- End-to-End ML Pipeline Development
- Dashboarding and Web App Deployment (Flask, Streamlit)
- Scalable ML System Design and Production Readiness
- Business-driven Data Science and Decision Support
Timeline
SOFTWARE ASSOCIATE
ZUVA ENGINEERING PVT.LTD
12.2020 - 04.2024
Master of Science - Computer And Information Sciences
Sacred Heart University