IAM Setup for Bedrock: Understanding Permissions, Roles, and Trust Policies

In this video, we walk through the IAM setup required for Amazon Bedrock batch inference, explaining not just the steps but why each permission exists and how to think about AWS security from first principles.

You'll learn how to:
Understand the three actors in a Bedrock workflow: user, service, and S3
Create user groups and assign permissions for your team
Set up execution roles for AWS services to access resources
Configure trust policies that allow services to assume roles
Add PassRole permissions to control who can assign roles
Think through IAM requirements from a security and compliance perspective
Apply this mental model to any AWS service integration

Timestamps:
0:21 - Three goals for understanding IAM complexity
1:18 - Batch inference use case and process flow
2:59 - The three actors: user, Bedrock service, and S3
3:25 - User groups and user permissions explained
4:44 - Execution roles: how services get permissions
6:21 - Trust policies: controlling which services can assume roles
8:17 - PassRole permissions: who can assign roles to services
9:46 - Real-world enterprise perspective and compliance requirements

This video helps you understand the reasoning behind AWS IAM so you can apply these patterns to SageMaker, Lambda, Step Functions, and other managed services.

This video is part of the LLM Engineering and Deployment Certification Program by Ready Tensor.

Enroll Now:
https://app.readytensor.ai/certificat...

About Ready Tensor:
Ready Tensor helps AI/ML professionals build production-grade LLM systems through hands-on certifications and real-world projects.

Learn more: https://www.readytensor.ai/

Like the video? Subscribe for more AWS and LLM engineering tutorials!