Get in Touch

Course Outline

Foundations of Production Deployment

  • Primary obstacles in deploying fine-tuned models
  • Contrasting development versus production environments
  • Overview of deployment tools and platforms

Model Preparation for Release

  • Exporting models using standard formats (such as ONNX, TensorFlow SavedModel, etc.)
  • Tuning models to maximize latency and throughput
  • Validating models against edge cases and real-world datasets

Containerization Strategies

  • Overview of Docker
  • Building Docker images specifically for ML models
  • Best practices for maintaining container security and efficiency

Scaling with Kubernetes

  • Applying Kubernetes to AI workloads
  • Configuring Kubernetes clusters for model hosting
  • Managing load balancing and horizontal scaling

Ongoing Monitoring and Care

  • Setting up monitoring using Prometheus and Grafana
  • Implementing automated logging for error detection and performance tracking
  • Establishing retraining pipelines to handle model drift and updates

Security in Production

  • Protecting APIs used for model inference
  • Implementing robust authentication and authorization mechanisms
  • Mitigating data privacy risks

Practical Applications and Labs

  • Deploying a sentiment analysis model
  • Scaling a machine translation service
  • Setting up monitoring for image classification models

Recap and Future Directions

Requirements

  • Solid grasp of machine learning workflows
  • Proven experience in fine-tuning ML models
  • Working knowledge of DevOps or MLOps principles

Intended Audience

  • DevOps Engineers
  • MLOps Practitioners
  • AI Deployment Specialists
 21 Hours

Number of participants


Price per participant

Testimonials (2)

Upcoming Courses

Related Categories