Stage 6 of 6 · Expert

AI Engineer

Under the hood: transformers, RAG, evals, tuning and inference.

For engineers building production AI systems. Understand the transformer and mixture-of-experts architectures, build retrieval that works, run evals in production, decide when to fine-tune, optimise inference cost, and understand how labs make models safe.

0/6

modules

minutes total

Modules

1
Transformers and mixture-of-experts
10 min
Attention, embeddings, scaling laws and why most frontier models are now sparse.
Start here →
2
Retrieval-augmented generation
10 min
Grounding models in your data: chunking, embeddings, hybrid search, reranking and evaluation.
3
Evals in production
9 min
Offline test sets, online monitoring and regression gates for AI features.
4
Fine-tuning and distillation
9 min
When prompting is not enough: supervised fine-tuning, preference tuning, RL and distillation.
5
Inference optimisation
9 min
KV caches, batching, quantisation, speculative decoding and prompt caching.
6
Alignment, safety and interpretability
9 min
How labs try to make models helpful, honest and harmless, and how they check.