Machine Learning is typically projected as data preparation or model building. It is not practised as deployment in terms of application. On average, AI practitioners used to spend 25% of their time setting up the environment though they have better work to do. Due to these up to 75% of AI projects stays as empirical experiments. These workshops focused to suppress these barriers by practising MLDevOps. We will be practising set of methods used to automate the lifecycle of machine learning algorithms in production — from initial model training to deployment to retraining against new data.

This workshop enables you to track, version, test, certify and reuse assets in every part of the ML lifecycle and provides orchestration practice to manage this lifecycle.

Kamal NS

AI practitioner at RBG.AI

Barathi Ganesh HB

Research head at RBG.AI


ML Structurization: "Coding is an art", let us perceive it by practising pipelines through functions and classes to think like an AI artist.

Version Control: "AI is full of uncertainty", where updates and upgrades are oblivious. So let we practice tracking and managing changes we made to software code.

Model Serving: "Consume what you have built", let us host your trained model as REST/Socket service to use it in practical applications.

Containerization: "Get rid of the dependencies", let us make a product that uses OS-level virtualization to deliver software without the dependency constraints.

Interactive Application: "Enrich the Exposure", let us learn a great way to share machine learning models and analyses with interactive front-ends.

CI/CD: "Focus on your core tasks", so let us establish continuous integration and continuous delivery (СI/CD) practices for deploying and updating machine learning pipelines in less time.


Students and research scholars with a background in AI are encouraged to participate. Our workshop’s primary focus is moving academic research works to industry applications -- so please participate only if you similarly have an impact-oriented mindset. The "Culture of Continuous Learning" is necessary for human as well as our ML algorithms.


If you have queries about our work, contact us at: