Skip to content
A.B. Labs

AI / Machine Learning

Applied AI & LLM Engineering

Design, build and evaluate applications powered by large language models — from prompt design and RAG to agents, evaluation and deployment.

Register interestView curriculum

Overview

Large language models have changed what software can do, but building reliable LLM applications takes real engineering. This course covers the full workflow: how models behave, how to ground them in your own data with retrieval, how to evaluate their output and how to deploy them responsibly.

You will build working AI applications with Python and FastAPI, and learn to reason about quality, cost, latency and safety — the questions that separate a demo from a product.

Who it's for

  • Developers who want to build AI-powered products
  • Learners who have completed Python for AI & Machine Learning, or have equivalent experience
  • Engineers adding LLM features to existing systems

Before you start

  • Working knowledge of Python
  • Familiarity with APIs and JSON
  • Basic machine learning concepts are helpful

Outcomes

What you'll learn.

  1. 01

    Explain how LLMs work — and where they fail

  2. 02

    Design effective, testable prompts and structured outputs

  3. 03

    Build retrieval-augmented generation (RAG) pipelines

  4. 04

    Create tool-using agents with clear boundaries

  5. 05

    Evaluate LLM systems with automated and human review

  6. 06

    Deploy AI features behind production-ready APIs

Curriculum

Module by module.

  1. Module 01How LLMs Work
    • Tokens, embeddings and transformers — intuitively
    • Capabilities, limits and failure modes
    • Choosing between hosted and open models
    • Cost, latency and context windows
  2. Module 02Prompt & Output Design
    • Instructions, examples and system prompts
    • Structured outputs and schema validation
    • Versioning and testing prompts
    • Handling ambiguity and refusals
  3. Module 03Embeddings & Vector Search
    • Semantic similarity and embeddings
    • Chunking strategies for documents
    • Vector databases and hybrid search
    • Measuring retrieval quality
  4. Module 04Retrieval-Augmented Generation
    • End-to-end RAG pipeline design
    • Grounding, citations and freshness
    • Re-ranking and query rewriting
    • Common RAG failure patterns
  5. Module 05Tools & Agents
    • Function calling and tool use
    • Planning and multi-step workflows
    • Keeping agents safe and bounded
    • When not to use an agent
  6. Module 06Evaluation
    • Building evaluation datasets
    • Automated metrics and model-graded evaluation
    • Human review workflows
    • Regression testing for AI features
  7. Module 07Production & Deployment
    • Serving AI features with FastAPI
    • Streaming, caching and rate limits
    • Observability and tracing
    • Privacy, security and responsible AI
  8. Module 08Capstone
    • Scoping an AI feature for a real problem
    • Build, evaluate and iterate
    • Deployment and documentation
    • Presenting trade-offs and results

Projects

What you'll build.

  1. 01

    A document question-answering assistant built on RAG

  2. 02

    An automated evaluation suite for an LLM feature

  3. 03

    A capstone AI application deployed behind a FastAPI service

We build this too

Need it built for you instead?

Machine learning models, LLM-powered applications and intelligent automation — designed around your data, evaluated rigorously and deployed into real products.

Explore AI / Machine Learning

Keep learning

Other courses.

  • AI / Machine Learning

    Upcoming

    Python for AI & Machine Learning

    Learn Python, data analysis and core machine learning by working with real datasets — the practical foundation for building with AI.

    Level
    Beginner
    Duration
    12 Weeks
    • Python
    • NumPy
    • pandas
    • Matplotlib
    • scikit-learn

  • App Development

    Upcoming

    Modern App Development with Flutter

    Build and ship cross-platform mobile apps with Flutter and Dart — from your first widget to a complete, release-ready app.

    Level
    Beginner to Intermediate
    Duration
    12 Weeks
    • Flutter
    • Dart
    • BLoC
    • Firebase
    • Riverpod

FAQ

Course questions.

Who are the courses for?

Most courses start from the fundamentals and suit motivated beginners. More advanced courses list their prerequisites clearly on the course page, so you can choose the right starting point.

How are the courses taught?

Every course is project-based: you learn a concept, then apply it by building something real. Schedules, delivery format and fees are announced with each cohort — register your interest and we will share the details once they are confirmed.

Do I need prior experience?

Not for beginner-level courses. Each course page lists its level and prerequisites. If you are unsure which course fits, contact us and we will help you decide.

Will I build real projects?

Yes — projects are the core of every course. Each course page lists the projects you will build, ending with a capstone that brings everything together.

Do you offer training for teams?

If you are interested in training for a team or organization, get in touch and choose “Training”. Tell us about your team, its current skills and what you want to achieve.

Not sure where to start?

Let's find the right course.

Tell us about your background and goals, and we'll help you choose a starting point.

Talk to usOur services