Generative AI Application Engineering

AT A GLANCE

Is this programme for you?

Built for ai, full-stack, backend developers. AI helps you move faster; every output is checked against references, runnable examples or a human review before you rely on it.

Register interest Ask about mentorship

Who it's for: AI, full-stack, backend developers
IT domain: Generative AI and LLM Applications (Intermediate)
Prerequisites: Backend Application Engineering; APIs and Integration
How AI is used: Core AI curriculum
Reviewed output: Streaming AI feature with output validation
How work is checked: Check against references, runnable examples or domain review; record uncertain outputs
Trainer: Trainer to assign
Status: Planned · dates and fees not yet set

CORE CONCEPTS

10 concepts, each with a practice brief.

Each concept ends in evidence you can show. Briefs are starting points and are reviewed by the trainer before publication.

01
Tokens and tokenization
Implement a focused example of Tokens and tokenization within a small part of Streaming AI feature with output validation; demonstrate a normal and an edge or failure case.
ImplementIntermediateEvidence: Small working lab and checksIWA-C30-01
02
Language model inference
Implement a focused example of Language model inference within a small part of Streaming AI feature with output validation; demonstrate a normal and an edge or failure case.
ImplementIntermediateEvidence: Small working lab and checksIWA-C30-02
03
Prompt context and instructions
Implement a focused example of Prompt context and instructions within a small part of Streaming AI feature with output validation; demonstrate a normal and an edge or failure case.
ImplementIntermediateEvidence: Small working lab and checksIWA-C30-03
04
Structured model outputs
Implement a focused example of Structured model outputs within a small part of Streaming AI feature with output validation; demonstrate a normal and an edge or failure case.
ImplementIntermediateEvidence: Small working lab and checksIWA-C30-04
05
Streaming model responses
Implement a focused example of Streaming model responses within a small part of Streaming AI feature with output validation; demonstrate a normal and an edge or failure case.
ImplementIntermediateEvidence: Small working lab and checksIWA-C30-05
06
Multimodal inputs and outputs
Implement a focused example of Multimodal inputs and outputs within a small part of Streaming AI feature with output validation; demonstrate a normal and an edge or failure case.
ImplementIntermediateEvidence: Small working lab and checksIWA-C30-06
07
Tool-calling interfaces
Implement a focused example of Tool-calling interfaces within a small part of Streaming AI feature with output validation; demonstrate a normal and an edge or failure case.
ImplementIntermediateEvidence: Small working lab and checksIWA-C30-07
08
Context-window management
Implement a focused example of Context-window management within a small part of Streaming AI feature with output validation; demonstrate a normal and an edge or failure case.
ImplementIntermediateEvidence: Small working lab and checksIWA-C30-08
09
Hallucinations and uncertainty
Implement a focused example of Hallucinations and uncertainty within a small part of Streaming AI feature with output validation; demonstrate a normal and an edge or failure case.
ImplementIntermediateEvidence: Small working lab and checksIWA-C30-09
10
LLM application cost and latency
Implement a focused example of LLM application cost and latency within a small part of Streaming AI feature with output validation; demonstrate a normal and an edge or failure case.
ImplementIntermediateEvidence: Small working lab and checksIWA-C30-10