Leading more than 20 most talented Network Engineers, Software Developers and Data Scientist to build and maintain the World’s most reliable cloud. Network Health is part of Azure Networking and responsible for making sure Physical Network Infrastructure is running healthy and error free. To achieve that we are working towards 100% automation for all live site scenarios. Detecting customer pain with the help of Machine Learning prediction model. Removing customer pain with automation before it can impact services. These are a couple of tough problems we are solving: Hardware Failure Prediction with ML. Hardware Failure Analysis and Grey Packet Drop detection. Automation to scale large network within seconds mitigation and detection. Monitoring and Detection without human touch for more than 500K Network Devices. Building and running services to support this scale of infrastructure. AI-OPS Modelling to remove all failure points. Writing the world-class in-house software SONIC – Open source. Testing and onboarding new hardware/software platforms