Model deployment strategies

MLOps Deployment and Life Cycling

Nemanja Radojkovic

Senior Machine Learning Engineer

Deployment successful!

• ML app is running
• API handles 1000s of requests/hour
• One month later:
  • New, better features found
  • Collected new batch of training data
  • Ran the model build pipeline
  • New model package created

Let's practice!

MLOps Deployment and Life Cycling