What you'll be able to do
- ✓Choose the right Redis data structure for each part of an AI workload
- ✓Design conversation memory that survives restarts and failover
- ✓Configure persistence, replication and cluster topology with intent
- ✓Measure and cut inference spend with a well-placed cache
Who it's for
Backend and platform engineers running AI features in production.
Contents
- 01The data layer behind an LLM product
- 02Strings, hashes, streams and sorted sets in practice
- 03Conversation memory and session state
- 04Persistence, replication and failover
- 05Cluster sizing and cost modelling
- 06Production incident walkthroughs
