Managed deployment on AWS

Data scientists and machine learning practitioners working on developing machine learning models to solve business problems are often very focused on model development. Problem formulation and developing an elegant solution, choosing the right algorithm, and training the model so that it provides reliable and accurate results are the main components of the machine learning problem solving cycle that we want our data scientists and data engineers to focus on.

However, once we have a good model, we want to run real-time or batch inference on new data. Deploying the model and then managing it are tasks that often require dedicated engineers and computation resources. This is because, we first need to make sure that we have all the right packages and libraries for the model to work correctly. Then, we also need to decide on the type and amount of compute resources needed for the model to run. In real-time applications, we often end up designing for peak performance...