Waltsoft
Blog
Engineering notes from Waltsoft on agentic AI, security and platform operations on AWS.
- aws lambda
- gpu
- lambda managed instances
Migrate GPU Podcast rendering from EC2 to Serverless on Lambda Managed Instances (LMI) with 90 min async runs
Our video podcast renders on a GPU once a week, and an AI agent runs it. What it took to move that to Lambda Managed Instances, cut the render from 5 hours to about 1, and keep the agent away from the GPU bill.