← All 186 courses
AI-107 AI & Data

Generative AI Foundations

A rigorous but accessible tour of how modern generative models work — tokenization, attention, pre-training, alignment — and the ecosystem around them: model families, hosting options, cost models and capability boundaries. Sets the conceptual base for every LLM engineering course that follows.

B2Foundation
5modules
33skill atoms
7role journeys
Curriculum

What this course covers.

5 modules, 33 named skill atoms. Expand any module to see them.

1From N-grams to Transformers6 skill atoms
language modelingwhy attention wonMarkov assumptionsRNN bottlenecksparallel trainingsequence-length scaling
2Inside an LLM7 skill atoms
tokensembeddingsattentiongeneration loopBPE tokenizationlogits & softmaxsampling vs greedy
3Training & Alignment7 skill atoms
pre-trainingfine-tuningRLHF at a concept levelnext-token objectiveinstruction tuningpreference datareward models
4Model Landscape6 skill atoms
open vs hostedcontext/cost/latency trade-offsopen-weight vs API-only familieslicence termsparameter count vs capabilityquantized variants
5Hands-on Playground7 skill atoms
API callsparametersstreamingfirst mini-apptemperature & top_psystem promptsrate-limit handling
Where it fits

AI-107 in the role journeys.

This course appears in 7 of our 45 role journeys. Here is what a learner takes immediately before and after it in each.

GenAI / LLM Engineer

Foundation stage
AI-106AI-107AI-101

Agentic AI Engineer

Foundation stage
AI-106AI-107AI-301

AI Architect

Foundation stage
starts hereAI-107AI-302

Forward Deployed Engineer

Foundation stage
AI-106AI-107AI-301

AI Quality / Eval Engineer

Foundation stage
AI-106AI-107AI-101

AI Security Engineer

Foundation stage
starts hereAI-107SEC-101

Solutions / Sales Engineer

Foundation stage
AI-106AI-107AI-505

Roles this course serves

The capability ladder

This course is authored to band B2.

Every course we run is written to one rung of the CASI ladder, so a plan can be assembled to take a team from where they are to where they need to be.

What do B1–B6 mean?The CASI Capability Ladder — click to expand

Every course targets a band on the CASI Capability Ladder — our six-band proficiency scale, anchored to open standards (O*NET, ESCO, NICE, NIST AI RMF, Bloom's). A band tells you how deep a course goes, and what evidence proves it.

What the learner can doTypical evidence
B1
AwareUnderstands concepts and vocabulary; uses tools with guidance
Knowledge checks
B2
FoundationPerforms standard tasks correctly in familiar contexts
Guided labs, autograded exercises
B3
PractitionerDelivers complete pieces of work independently
Scenario labs, proctored hands-on exams
B4
ProfessionalHandles production-grade complexity, trade-offs and failure modes
Break-fix drills, design defenses
B5
AdvancedEngineers systems end-to-end under constraints; leads others
Rubric-scored capstones, vivas
B6
ExpertSets direction; recognised authority across teams
Portfolio + panel evaluation

A note on B6. Courses in this catalog target B1–B5. B6 is not taught — it is recognised, through a portfolio and a panel, once someone is setting direction for others. Every journey here is built to land a learner at B5.

Next step

Run AI-107 for your team.

This course runs at several lengths depending on how deep you need to go and how much of it your people already have. Tell us who is being trained and we will scope it.

Add it to a training plan Talk to our team Check your team’s level free