Prasanth Siddireddi

About Prasanth Siddireddi

As a Data Engineer with 4+ years of experience, I specialize in building scalable data…

Experience

1. Data Engineer

   Mastercard

   Dec 2024 — Present · US

   Engineered and optimized large-scale data ingestion frameworks using Python and AWS services, improving end-to-end data processing efficiency by 30%.• Integrated, deployed, and maintained machine learning pipelines within AWS SageMaker, enabling predictive analytics for fraud detection, anomaly detection, and risk mitigation scenarios.• Developed, automated, and enhanced robust data preprocessing workflows for cleansing, transformation, and feature extraction, significantly improving downstream machine learning model training accuracy.•Orchestrated, managed, and scaled Apache Kafka infrastructure with Spark Streaming, delivering resilient, high-volume, low-latency data pipelines supporting enterprise-grade analytical workloads.• Designed and implemented hybrid architectures by combining Spark, Kafka, and AWS S3 batch/streaming pipelines, ensuring scalability, availability, and seamless enterprise integration.• Built, evaluated, and monitored predictive models for transaction risk scoring using Python, Pandas, and Scikit-learn, reducing fraud-related false positives by 20%.• Deployed, versioned, and continuously monitored production machine learning models using AWS SageMaker endpoints, integrating outputs into enterprise-wide data marts for analysts.