Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Overview of Production Deployment
- Primary obstacles associated with deploying fine-tuned artificial intelligence models
- Distinctions between development stages and operational production environments for government systems
- Available tools and platforms to support secure model deployment for government applications
Preparation of Models for Deployment
- Exporting models into standardized formats (e.g., ONNX, TensorFlow SavedModel)
- Optimizing architectures to meet latency and throughput requirements
- Validating model performance against edge cases and realistic data scenarios
Containerization for Model Deployment
- Fundamentals of Docker technology
- Procedures for constructing Docker images for machine learning models
- Best practices for ensuring container security and operational efficiency
Scaling Deployments with Kubernetes
- Application of Kubernetes for managing artificial intelligence workloads
- Configuration of Kubernetes clusters to host model services
- Strategies for load balancing and horizontal scaling to support demand
Model Monitoring and Maintenance
- Implementation of monitoring solutions using Prometheus and Grafana
- Establishment of automated logging systems for error tracking and performance analysis
- Development of retraining pipelines to address model drift and facilitate updates
Ensuring Security in Production
- Securing application programming interfaces (APIs) used for model inference
- Deployment of authentication and authorization mechanisms to control access
- Addressing data privacy requirements and compliance standards
Case Studies and Hands-On Labs
- Execution of a sentiment analysis model deployment
- Scaling procedures for a machine translation service
- Implementation of monitoring protocols for image classification models
Summary and Next Steps
Requirements
- Comprehensive knowledge of machine learning operational processes
- Demonstrated proficiency in the customization and refinement of ML models
- Familiarity with DevOps and MLOps methodologies
Targeted Stakeholders
- Infrastructure and operations engineers
- Machine learning operations professionals
- Specialists in AI system implementation for government
21 Hours
Testimonials (2)
Craig was extremely involved in the training, always making sure we are paying attention, adapted the examples to our day-to-day activities and always provided an answer when asked, even if the information was not added in the presentation.
Ecaterina Ioana Nicoale - BOOKING HOLDINGS ROMANIA SRL
Course - DevOps Foundation®
High level of commitment and knowledge of the trainer
