Nishaglobal Education logo

Tester / QA → AI Evaluation Engineer

Learn how AI works and why it fails, then specialise in measuring and improving AI quality as an AI Evaluation Engineer.

For: Testers, QA and test automation engineers. 20 lessons in this path.

Your progress

0 of 13 published lessons completed

Start lesson 1: What AI really is (and what it isn't) →

Progress is saved in this browser. No account needed.

Step 1

Foundations

How AI works, why it fails, how to ask it well and how to use it safely.

  1. 1What AI really is (and what it isn't)
  2. 2How machines learn: data, training and models
  3. 3How large language models work
  4. 4Why AI gets things wrong: hallucinations, bias and limits
  5. 5Prompting fundamentals: getting useful answers
  6. 6Using AI safely at work

Step 2

Practitioner

The building blocks behind real AI products, explained without code.

  1. 7Advanced prompting and structured output
  2. 8Embeddings and semantic search
  3. 9Retrieval-augmented generation (RAG)
  4. 10Tool calling and AI agents
  5. 11Evaluating AI quality
  6. 12Cost, speed and scale
  7. 13AI across the software lifecycle

Step 3

Track: AI Evaluation Engineer

Measure and improve AI quality. For testers and QA moving into AI evaluation.

  1. 19An evaluation strategy for AI featuresComing soon
  2. 20Building evaluation datasetsComing soon
  3. 21Metrics, rubrics and LLM-as-judgeComing soon
  4. 22Red teaming and adversarial testingComing soon
  5. 23Evaluation in CI and productionComing soon

Step 4

Capstone and career

Put it all together, build proof of your skills and plan your next role.

  1. 37Capstone projects by roleComing soon
  2. 38Your AI career planComing soon

Other learning paths

💻 Developer📋 Business Analyst / PO🏗️ Tech Lead / Architect📈 Project / Delivery Manager🔄 Scrum Master / Agile