Admissions are open for the October cohort. Explore Tracks
TTabflux

Skill Course

LLM, Multimodal & Generative AI Foundations

Understand and integrate the model capabilities behind modern generative AI products.

15 Hours + 6 Hours
View objectives

Learning objectives

01

Explain key LLM and multimodal concepts

02

Select models based on capability, cost and latency

03

Integrate text and multimodal model APIs

04

Generate validated structured outputs

05

Recognize model risks and responsible-use constraints

Course coverage

01

Generative AI, foundation models, LLMs, transformers and inference fundamentals

02

Tokens, embeddings, context windows, sampling, temperature and model behavior

03

Major AI providers and APIs: OpenAI, Anthropic, Gemini, Bedrock and open-source models

04

Chat and completion APIs, streaming, structured outputs and function/tool calling

05

Embeddings, semantic similarity and vector-representation fundamentals

06

Multimodal AI: text, vision, audio, speech and document understanding

07

Model selection, capabilities, limitations, hallucinations and reliability

08

Token usage, latency, model pricing, cost and provider tradeoffs

Next recommended Skill Course

Prompt Engineering Fundamentals

Design reliable instructions, context, examples, and outputs for model-powered software.