Rohith Reddy

Driving AI innovation in financial systems by architecting and deploying scalable ML solutions for trading, risk modeling, and portfolio optimization. Leading cross-functional teams to deliver explainable, compliant, and high-performance AI systems using AWS SageMaker, TensorFlow, and PyTorch. Passionate about advancing model governance, real-time inference, and Generative AI adoption to enhance decision intelligence across capital markets.

AI/ML Engineer with expertise in healthcare analytics, predictive modeling, and scalable ML solutions on AWS. Skilled in building end-to-end ML pipelines, leveraging TensorFlow, PyTorch, and NLP on clinical data to improve patient care and operational efficiency. Experienced in CI/CD, Docker/Kubernetes, data lakes, and HIPAA-compliant ML workflows, delivering actionable insights through dashboards and interpretability tools like SHAP/LIME. Passionate about turning complex healthcare data into impactful AI solutions and collaborating with cross-functional teams to drive innovation.

As a Data Scientist, I led end-to-end development of machine learning solutions for credit risk, fraud detection, and customer analytics within the banking domain. I built and deployed scalable ML pipelines using Azure Machine Learning, Data Factory, and Synapse Analytics, enabling real-time decision systems and predictive insights. My work improved default prediction accuracy by 18% and optimized credit approval turnaround time through Azure-based automation. I applied NLP, time series forecasting, and MLOps best practices to enhance customer retention, profitability, and operational efficiency. Collaborating cross-functionally with risk, finance, and IT teams, I ensured all models met Fair Lending, explainability (SHAP/LIME), and governance standards, driving data-driven transformation across the organization.

As a Data Scientist at H-E-B, I developed and deployed predictive and prescriptive analytics solutions across marketing, supply chain, and customer experience domains. I built scalable machine learning models for segmentation, forecasting, and recommendation systems using Azure Machine Learning, Databricks, and Spark. My work enhanced personalization, optimized inventory management, and improved campaign efficiency. I also automated data pipelines on Azure Data Factory, created interactive Power BI dashboards, and ensured data governance across cloud environments

Built and automated ETL pipelines for large-scale telecom data, improving real-time analytics and reporting. >Designed scalable data warehouses using Amazon Redshift and SQL to support telecom performance insights. >Developed batch and streaming workflows with Apache Spark and Kafka for near real-time data processing. >Migrated legacy systems to AWS (S3, EMR, Lambda), enhancing scalability and cost efficiency. >Improved query performance and data reliability through partitioning, indexing, and validation frameworks. >Enabled BI and ML initiatives by preparing telecom datasets for customer insights and churn prediction.