Generative AI with Large Language Models
Reviewed by AI Agent Rank editors · Last verified 2026-05-23
Our take
The most comprehensive LLM-internals course in the under-20-hour bucket. Covers transformer architecture, pretraining, fine-tuning (instruction + PEFT/LoRA), RLHF, and deployment-side concerns (cost, throughput, scaling). Built on AWS Bedrock for labs, but the architectural content transfers to any platform. Skip if you already know how transformers work — most of the value is in the middle weeks on fine-tuning and RLHF, which is harder to find elsewhere.
About the instructor
Senior AWS-side specialists who built much of the Bedrock platform onboarding.
Pros
- +Best treatment of fine-tuning + RLHF in any short-form course
- +Auditable for free — you only pay for the Coursera Plus certificate
- +Hands-on AWS Bedrock labs (transferable patterns)
Cons
- −AWS-specific labs — if you don't have an AWS account, the lab portion is awkward
- −16-hour commitment is a real ask for non-engineers
Best for
- · Engineers who plan to fine-tune or self-host LLMs
- · Anyone evaluating "should we fine-tune or just use a bigger model?"
Not ideal for
- · Beginners — assumes ML basics (gradient descent, embeddings)
- · People who only want to use LLM APIs, not understand them
Free to audit · $49 cert on Coursera · ~16 hours (3 weeks at 5h/wk)
Alternatives we considered
Other courses on the same topic. The right pick depends on your level and constraints — see each card for the trade-offs.