I am a researcher working in Internet measurements at the intersection between Deep Learning, BigData and data-plane programming. Currently, I am a Principal Engineer working in AI4NET Datacom lab lead by Dario Rossi, at the Huawei Research center in Paris (France), and I focus on the integration of Deep Learning into traffic monitoring systems, targeting continuous learning and network automation.
Previously, I was an associate researcher at Telefonica Research, and a Principal Engineer at Telefonica UK/O2, where I designed and deployed an ML product to predict daily customer satisfaction for 30M+ O2 customers using a variety of live network logs.
I currently work in the AI4NET group at the Datacom department of Huawei Research in Paris. We work focuses on the integration of DL into network monitoring and distributed telemetry systems, specifically touching few-shot learning, and continuous learning.
Started as research experiment and later graduated to product, I lead a project aim to create a ML model to predict the satisfaction of the 30M+ O2 customers. The system was based on a combination of Apache Spark analytics and sklearn modeling, and deployed on a 250+ nodes hadoop cluster generating daily predictions using a wide variety of network data feeds from the mobile network packet core. The prediction have been succesfully used to drive operations for both marketing campains and radio teams planning at O2/Telefonica UK.
I split my time between doing Internet measurements research, and support different Telefonica operational business (OBs) needs for analytics based on network data.
I worked on different research projects related to network measurements, and spent almost 1 year at Narus Inc (now part of Symantec) focusing on cyber security based on network traffic analytics.