Episode · Apr 30, 2026
How to Engineer AI Inference Systems
The TWIML AI Podcast
We use cookies for analytics.
Podcast, The TWIML AI Podcast
Hosted by Sam Charrington
Sam Charrington and Sadeepa Wijesekara discuss how enterprises decide which AI inference to run locally and which to buy from hosted providers. They cover cost per model call, routing to different models by workload, and how privacy constraints and GPU economics shape deployment.