Salesforce Achieves Multi-AZ HA with SageMaker Inference Components

Rielah De Jesus· August 28, 2026 View original

Key takeaways

  • Salesforce used SageMaker Inference Components for Multi-AZ high availability.
  • The `SchedulingConfig` parameter enabled model distribution across AZs.
  • This approach met compliance without sacrificing multi-model co-hosting cost efficiency.
  • It provides a blueprint for resilient AI inference deployments.

Who benefits

Cloud ComputingSoftware DevelopmentEnterprise ITFinTech

Summary

Salesforce successfully used Amazon SageMaker AI Inference Component placement to distribute model copies across multiple Availability Zones, fulfilling their Multi-AZ high availability compliance needs. This approach maintained the cost efficiency of multi-model co-hosting while ensuring robust system resilience.

Salesforce has detailed its strategy for achieving multi-Availability Zone (Multi-AZ) high availability for its AI inference workloads using Amazon SageMaker. By leveraging SageMaker's Inference Component placement feature, specifically the `SchedulingConfig` parameter, Salesforce was able to strategically distribute copies of its machine learning models across different Availability Zones. This method allowed them to meet stringent high availability compliance requirements, ensuring continuous service even in the event of an AZ failure. Crucially, this was accomplished without compromising the cost-effectiveness typically associated with co-hosting multiple models on shared infrastructure.

Why it matters

For professionals building and deploying AI models, this demonstrates a practical and cost-effective method to ensure high availability and resilience for critical inference services, a key concern for enterprise-grade applications.

How to implement this in your domain

  1. 1Review current AI model deployment strategies for single points of failure.
  2. 2Investigate Amazon SageMaker Inference Components and the `SchedulingConfig` parameter.
  3. 3Design a multi-AZ deployment architecture for critical AI inference endpoints.
  4. 4Implement and test the distribution of model copies across different Availability Zones.
  5. 5Monitor the high availability and cost efficiency of the new deployment.

Original post by Rielah De Jesus

"Learn how Salesforce used Amazon SageMaker AI Inference Component placement (the SchedulingConfig parameter) to distribute model copies across multiple Availability Zones, meeting their Multi-AZ high availability compliance requirements without sacrificing the cost efficiency of…"

View on X

Originally posted by Rielah De Jesus on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses