Tubi is an advertiser based video on demand (AVOD) service that allows users to watch content available online for free with ads. There are three key pillars in an AVOD service, namely, content, audience and ads. These three pillars necessitate the application of Machine Learning to help improve the overall product. In this talk, I will present some of the lessons learned and unsolved challenges in productionizing large scale recommender and content understanding systems. Jaya Kawale is the VP of Engineering at Tubi, leading all the Machine Learning efforts at the company. She did her PhD in Computer Science from the University of Minnesota on Graph based approaches for spatio-temporal datasets. Her thesis won several awards including the "Explorations in Science through Computation" award presented at the Super Computing conference. She has published several papers in top tier conferences and has authored several patents. In the past, she has worked at Netflix, Adobe Research, Microsoft Research and Yahoo Research. ✅ Connect with Jaya: https://www.linkedin.com/in/jayakawale/ ✅ Connect with Optimized AI Conference on LinkedIn - https://www.linkedin.com/company/oaiconference/ ✅ Connect with Optimized AI Conference on Twitter: https://x.com/southerndsc ✅ Visit Optimized AI Conference Website - https://www.oaiconference.com/