Inference engineering curriculum

Fanout's inference engineering course is for backend, ML, and platform engineers moving from model demos to production traffic.

Start with inference fundamentals and your first language model, then study KV caches, batching, quantization, serving runtimes, distributed execution, benchmarking, and observability.

The curriculum connects explanations, videos, and exercises to production decisions. Introductory lessons are free; Pro unlocks the full course.

Practice and Code are being refined. Interview questions will unlock soon.