Currently, I work for Azure and my focus lies in addressing following three key areas: Scalable Raw Data Collection: I'm deeply engaged in optimizing the collection of raw data at a massive scale across Azure networks. My interest particularly centers around efficiently distributing data loads across diverse geographies, ensuring seamless operations and data integrity. Pattern Recognition and Anomaly Detection: I specialize in leveraging advanced pattern recognition techniques to find anomalies and identify unhealthy signatures within network data. My goal is not just to detect issues, but to anticipate them, proactively spot them before they manifest into critical problems. Automated Remediation for Self-Healing Networks: I'm committed to building self-healing networks by implementing automated actions to remediate identified anomalies swiftly and effectively. Using automation, I aim to enhance network resilience and minimize downtime. 🚀 Excited to be at the forefront of innovation in cloud technology, I'm dedicated to driving impactful solutions that empower organizations to harness the full potential of Azure while ensuring robust device health and cloud performance. Previously I completed my masters from Georgia tech with specialization in Machine learning. During my grad studies I have worked on semi supervised learning for textual data. I also worked as Teaching assistant for grad level Intro to Artificial intelligence. In the past I also had the privilege to contribute to opensource community- OpendayLight: A Software Defined Controller.