Deepgram enhances Amazon SageMaker AI support with AWS IAM Temporary Delegation
AWS Machine Learning Victor Wang
Deepgram integrated AWS IAM temporary delegation into its speech AI models running on Amazon SageMaker to enable support engineers to access customer endpoints without long-lived credentials or cross-account roles. The integration reduces initial support investigation time from days to minutes by letting customers approve scoped, twelve-hour access requests directly in their IAM console, with all actions logged in CloudTrail. This provides enterprises with auditable, time-bounded support access while maintaining data residency and compliance requirements.
Why it matters
In this post, we cover why Deepgram built on IAM temporary delegation, how the integration works end-to-end, and what it unlocks for customers running Deepgram speech models on SageMaker AI. With this integration, Deepgram has reduced the time for initial investigation on a SageMaker AI support ticket from days to minutes.
