Pavan Kumar Adapala

Achieved 95% accuracy in forecasting energy consumption of automotive paint shop by developing machine learning models. Managed data integrity by excluding the commissioning period, performing plausibility checks, and feature generation, enhancing quality by 30%. Developed and evaluated machine learning models using batch and one-step ahead forecasting approaches for three distinct business use cases to deliver robust forecasting insights.

Developed basic designs and optimized Jenkins CI/CD pipelines to automate build, test, and deploy processes for autonomous parking software. Reduced root-cause analysis time by 30% in the software development process by implementing a Python automation script to extract and summarize test results (integration, APS/OPS) from Jenkins build artifacts. Designed and implemented a centralized Grafana dashboard for real-time Jenkins jobs monitoring across parking software projects to increase productivity.

Automated AWS infrastructure deployment with CloudFormation, improving scalability, availability, and security while reducing manual effort. Automated incident detection and response by integrating AWS CloudWatch alerts with Amazon Simple Email Service (SES), enabling real-time notifications for system anomalies. Developed AWS CloudWatch dashboards and logging solutions to monitor application performance, optimize resource utilization, and enhance system reliability.

Designed and deployed scalable, secure AWS cloud infrastructure to support enterprise applications. Developed and automated CI/CD pipelines using AWS CodePipeline, streamlining deployments across dev, test, and production environments. Implemented AWS CloudWatch for real-time monitoring and logging, improving system observability and proactive issue resolution. Collaborated with cross-functional teams to address infrastructure needs, troubleshoot deployment issues, and enhance system efficiency.