The needs of AI developers at LinkedIn go far beyond simple serving of models. In this talk, we will share our journey to serving complex real-world Machine Learning (ML) workflows. We will talk about how we leverage Ray serving now, and in the future. We will also discuss the solutions we are developing to address the growing complexity of AI-based applications and to make the work of AI engineers more productive.
Sasha Ovsankin is a Sr. Staff Engineer at the LinkedIn AI Platform focusing on Serving ML Workflows. He previously worked on Real Time Feature Engineering. Before joining the LinkedIn AI Platform Sasha worked on Machine Learning, Data and Analytics platforms at Uber, LinkedIn, and developed technology in a variety of fields such as sentiment analysis, search, image streaming and segmentation, graphic design.
Ali Naqvi is a Sr Staff Engineer at the LinkedIn AI Platform focusing on Serving ML Workflows. Before joining the LinkedIn AI Platform team Ali has worked on building ML infrastructure, Search Infrastructure and Recommender Systems at Anyscale, Uber and Yahoo.
Come connect with the global community of thinkers and disruptors who are building and deploying the next generation of AI and ML applications.