Effective MLOps
Objectives
This training aims to teach practical aspects of productionizing ML services from collecting requirements to model deployment and monitoring.
Benefits: Master a set of tools and practices that helps you create a reliable Machine Learning model and make it to production
Target Audience: Data scientists and ML engineers. Also, software and data engineers interested in learning about putting ML in production.
Pre-requisites:
- Python
- Docker
- Being comfortable with command line
- Knowledge on machine learning
- Prior programming experience (at least 1+ year)
The Program
Module 1 : Data, Model & Experiment Management
- What is MLOps
- MLOps maturity levels
- Introduction and data understanding
- Data cleaning and modeling
- Data, code, experiment versioning
Key learnings
- Learn ML & MLOps fundamentals
- Build and compare an end-to-end ML models
- Master Version Control System (DagsHub, GitHub)
Module 2 : Tooling, Infrastructure & Deployment
- Backend and Frontend parts (Create restAPI using FastAPI & Create frontend using Streamlit framework)
- Containerization (Docker)
- Deploy the application to cloud provider (AWS, Heroku)
- CI/CD/CT pipeline (Jenkins, GitHub Actions)
Key learnings
- Master deploying ML system
- Get hands-on experience in automatisation process for ML system
Module 3 : Serving, Testing and Validating the ML system
- Testing: unit, integration
- Testing data and models using Deepchecks
- Monitoring ML-based services
- Configure Arize AI as Machine Learning monitoring system
Key learnings
- Get hands-on experience in testing and monitoring for ML system
Effective SRE
Effective MLOps
ML for Life Sciences
ML4 DevOps
Interested in shaping your tailored training ?
Contact us at info@digital-innovation-partner.ch
