Level 8 of 9
Pro 2: Production engineer
At the end you can: Deploy, monitor and cache; control latency and cost; handle security and privacy.
About 30 hours in all; the steps written so far take about 25.
Steps
- Deploy and monitor an LLM appPut an LLM app online and watch its errors, latency, cost and answer quality.Not started · about 6 hours
- Caching and speedCut cost and waiting time with prompt caching, response caching and streaming.Not started · about 2 hours
- Inside LLM inference: prefill, decode and the KV cacheExplain why an LLM reply has a wait before the first word and a speed after it, size a KV cache, and pick the right lever for latency, throughput or cost.Not started · about 3 hours
Sign in or sign up to see the full roadmap
All 8 topics in order, with your progress saved on every device. It takes a few seconds, no card needed.
Accounts are for learners aged 18 and over. Under 18? Every lesson is still open: browse lessons by topic.
Level project
A deployed app with monitoring and a cost report.