Starts July 18
before agents
Track
LLM Engineer
Treat an LLM as an engineering system: tokens, context, transformers, inference, APIs, cost, grounding, and evals.
Private Discord community
Practice, quizzes, and a final project
Mentors and checkpoints
Lifetime access and updates
AboutWithout heavy mathematics, trace what happens between a prompt and a model response. Understand tokens, context windows, attention, pretraining and post-training, compare hosted and local inference, define a JSON output contract, and build a mini-eval. The cumulative exercise ends with an LLM-preflight for one scenario.
- Separate model weights, current context, application memory, and external data
- Understand tokens, attention, logits, sampling, and inference without heavy math
- Choose between prompting/context, RAG, fine-tuning, and memory for a specific problem
- Build an API contract, grounding plan, four-case mini-eval, and final LLM-preflight
LLM Engineer
Who this is for
New
Developers who need a working model of context, inference, APIs, and response quality
Pro
Product managers and analysts who use LLM features and need to reason about latency, cost, and model errors
Technical leads who choose models, review output contracts, and discuss evals with engineering teams
Beginners ready to understand LLMs without heavy mathematics or training a model from scratch
Future AI-agent developers who need the foundation before tools, memory, and orchestration
Curriculum
Seven modules move from model mechanics to an engineering contract for an LLM scenario and a bridge to agents.
01
Model Without Magic
02
Tokens and Context
03
Transformer in Plain Language
04
How Models Are Trained
05
Model, Inference, and API
Show more
Learning Platform
Short lessons, practice, and final artifacts live on one platform. Wallet login does not require a separate password.
- Wallet LoginConnect MetaMask from any device and resume where you stopped. You do not need a separate password.
- Short LessonsLessons are split into small blocks. Complete one in a short session, then resume from the same point later.
- Practice ThroughoutAssignments apply the material right after a lesson. In larger programs, separate outputs build toward a final project or capstone.
- One WorkspaceLessons, quizzes, assignments, and course materials stay together. Technical tasks can use the editor and syntax highlighting.
CommunityEach block ends with an assignment. Keep the intermediate results and assemble the final piece step by step.
Reviews and Community
01
Practice Reviews
Mentors review code, models, product decisions, and research artifacts in a format that fits each program.
02
Expert AMAs
Developers, researchers, and founders answer questions and show how they make decisions in real projects.
03
Research Briefings
The Guide DAO team follows new papers, tools, protocols, and working practices and connects them to the curriculum.
What You Leave With
Finish the program with a verifiable result you can show to a team or use in your next project.
Final Project
Build the program's main result against clear criteria and take it to a state another person can verify.
Portfolio of Work
Keep intermediate artifacts, sources, and decisions so others can see how you worked and why you reached the result.
Next Step
Record the result's limits, open questions, and next actions for your own project, a team, or a new role.