Get certified as an
AI EngineerApplied Readiness
Prove your ability to design, evaluate and improve modern AI applications using LLMs, RAG, tools, agents and production AI engineering practice - across four parts, against a published competency blueprint.
Built for AI Engineer, Applied AI Engineer, Generative AI Engineer and similar entry-level roles.
The assessment
25 min
timed assessment
20
technical + scenario + case questions
4
assessment sections
75%
passing standard
You will be assessed on
9 competencies, scored separately
Not one number called “AI Engineer”. Your result reports a level for each of these, so you can pass overall and still see exactly where the gap is.
LLM Application Fundamentals
How models behave in a real application, and how they are called.
Prompt & Context Engineering
Task definition, context selection, constraints and iteration.
Structured AI Outputs
Schemas, validation and enforcing a contract on unreliable output.
Retrieval & RAG
Embeddings, chunking, retrieval, grounding and provenance.
Tool Calling & Agents
Tool schemas, permissions, state and bounded autonomy.
AI Evaluation
Evaluation sets, grounding, trajectories and regression testing.
Reliability
Timeouts, retries, fallbacks, idempotency and observability.
AI Safety & Security
Prompt injection, sensitive data, authorization and consequential actions.
Production AI Judgment
Balancing quality, latency, cost and safety in a real deployment.
Assessment standard
Every attempt draws a fresh paper - but always the same number of questions from each competency area, so nobody gets an easier test.
LLM & AI Application Foundations
How models behave, what belongs in a prompt, and which work should not go to a model at all.
- LLM Behaviour & Context2
- Structured Outputs1
- Model Selection1
- AI vs Deterministic Code1
Retrieval, Tools & Agents
Embeddings, chunking and retrieval, and the difference between an agent and a workflow.
- Embeddings & RAG2
- Chunking & Retrieval1
- Tool Calling & Agents2
Evaluation, Reliability & Safety
Whether you can tell a working system from one that happens to look right, and what it does when it fails.
- AI Evaluation2
- Reliability1
- Safety & Security1
- Cost & Latency1
You must score at least 60% here, whatever your overall total.
Applied AI Engineering
Five production situations you answer in your own words: what you would build, and what you would check.
- Extraction & Reliability1
- RAG Debugging1
- Agent Safety1
- Evaluation & Readiness1
- Production Judgment1
You must score at least 60% here, whatever your overall total.
Assessment version
AI-ENGINEER-v1
Question bank
64 randomized items
Passing standard
75% weighted
Result bands
Distinction / Strong Performance / Certified
Result bands describe performance on this assessment. They are not a measure of employability or hiring outcomes.
Learning outcomes
These are what the public verification page reports - and each one is claimed only where your own attempt evidenced it.
LLM Application Engineering
Demonstrated understanding of how LLMs are integrated into practical application workflows using prompts, context, APIs and structured contracts.
Structured AI Outputs
Demonstrated ability to reason about schema-constrained generation, validation and safe handling of unreliable model output.
Retrieval-Augmented Generation
Demonstrated understanding of embeddings, retrieval, chunking, grounding, provenance and common RAG failure modes.
Tools & Agent Workflows
Demonstrated understanding of tool calling, permissions, state, bounded autonomy and when deterministic workflows are preferable to agents.
AI Evaluation
Demonstrated ability to reason about evaluation datasets, grounding, failure cases, agent trajectories and regression testing.
AI Reliability
Demonstrated understanding of retries, fallbacks, timeouts, idempotency, observability and safe production failure handling.
AI Safety & Security
Demonstrated judgment around prompt injection, sensitive data, tool permissions, authorization and consequential AI actions.
Production AI Judgment
Demonstrated ability to balance quality, latency, cost, safety and reliability when designing production AI systems.
How the written scenarios are graded
A model reading your answer and returning “8.7 out of 10” is not a grade - it is a guess with a decimal point. So we split the job in two: the AI only observes, and the code scores.
The evaluator reports which engineering decisions it can evidence in your own words - constrained the schema, separated retrieval from generation, bounded the retries, required authorisation for a consequential action. It has no score field to write into. Points come from a fixed rubric in code, so listing buzzwords with no mechanism behind them earns nothing.
Your written scenario answer
40-80 words, in your own words, in the time you have.
AI evaluator
Reports only which expected behaviours are evidenced, and which red flags appear.
Deterministic rubric
Code turns those observations into points, using the bank's own signal list.
Weighted result + competency profile
Part A 20%, Part B 25%, Part C 25%, Part D 30% decides the 75% pass mark; the same answers roll up into a level for each competency.
Where this fits
Each credential proves something different. You do not need all of them to start applying - but together they describe an engineer rather than a score.
Applied AI & ML Associate
Understands data and classical machine learning.
AI Engineer - Applied Readiness
Builds modern AI applications. You are here.
AI Work Competency
Uses AI effectively and responsibly while working.
Tech Workplace Competency
Operates effectively inside a technology team.
Weekly Ranking
Frequently asked questions
Free, 25 minutes, and a verifiable credential at the end.
This credential verifies applied AI engineering: LLM application design, retrieval, tools, agents, evaluation, reliability and safety. It is distinct from Applied AI & Machine Learning - Associate Readiness, which verifies classical machine-learning and data-science foundations. The two prove different capabilities and neither replaces the other.