Graphs are an excellent method to express complicated relationships and interdependencies between objects. It is widely used in traffic problems, malicious networks detection, social networks, biomedical networks, and more. Nonetheless, their complex structure is uniquely challenging when trying to extract insights in a way that would genuinely complement traditional ML techniques. At PayPal, we are dealing with massive scale graphs. We use advanced graph embedding methods based on Graph Neural Networks and apply them in a distributed manner to our production environment. In this poster, I will describe the challenges of graph processing as a non-euclidean data object and how to graph embedding can help overcome them. I will share how we used DGL (Deep Graph Library) to implement one of the most breakthrough graph embedding algorithms (GraphSAGE) for different applications and provide unique incremental insights to our models