My research interest span the areas of deep reinforcement learning (RL), networked system design, and performance analysis. I focused on building RL-based self-driving wireless network management system for quality of experience (QoE) optimization. In the past, I built non-traditional networking systems for challenged environments, with an emphasis on optimizing QoE on mobile broadband. I developed Lumos and Edain, two robust and scalable systems that accurately predict congestion and overload in LTE and 5G networks using only passive measurements. The applicability of these systems spans from independent network assessment to autonomous capacity planning.

I received my PhD in Computer Science from UC Santa Barbara where I worked in MOMENT Lab, advised by Prof. Elizabeth Belding.