Sri Charani

About Sri Charani

I’m a results-driven Data Engineer with 3+ years of experience designing and deploying machine learning solutions across industries like finance, operations, and risk analytics. Skilled in Python, SQL, Apache Spark, and TensorFlow, I’ve developed and productionized predictive models that improved decision accuracy by 28% and reduced manual processes by 40%. My background includes working at Cloudera and IBM, where I led projects involving EDA, feature engineering, model deployment (AWS, SageMaker, Cloudera AI), and monitoring pipelines to maintain 99.9% uptime. I’m passionate about transforming raw data into actionable insights and aligning data science outcomes with business goals through clear communication and executive-ready dashboards.

Experience

1. Data Engineer

   Cloudera

   Jun 2024 — Present

   Led the design and development of predictive models for fraud detection and customer segmentation, improving decision accuracy by 28%. Optimized ETL workflows using Apache Spark, Hive, and SQL, reducing latency by 40%. Engineered features and performed EDA using Python (Pandas, NumPy), boosting model performance. Implemented CI/CD pipelines using Jenkins and GitHub Actions to automate model deployment and version control. Monitored ML models using CloudWatch, MLflow, and Cloudera SDX, incorporating automated retraining pipelines, A/B testing, and model drift detection. Built and deployed machine learning models with scikit-learn, TensorFlow, and PyTorch; containerized and deployed via REST APIs using Docker, Cloudera AI, and AWS Lambda. Presented data-driven insights via interactive dashboards in Tableau and Seaborn to stakeholders. Created and maintained interactive dashboards with Tableau, Seaborn, and Plotly to present key performance indicators (KPIs).

Education

• Sacred Heart University

  Master's Degree, Computer and Information Sciences, General