Professor Gupta's research focuses on the development of self-driving networks, i.e., networks that run themselves with minimal human intervention. To achieve this goal, his research focuses on the design and implementation of systems that operationalize machine learning for network-management tasks, enabling the development of network automation tools that pave the way for self-driving networks. Currently, he is developing a robust packet-processing pipeline that can not only scale deep learning models by making the best use of limited network resources but also efficiently handle traffic dynamics. He is also developing an RL-based system that can detect, diagnose, localize, and fix network issues (e.g., outages) at the last mile (e.g., CMTS, home routers, etc.) as well as core (e.g., packet gateway)---improving the quality of experience for broadband networks.