Skip to content
NextiaNextia Learning

Learning path · Build AI

Software developer transitioning to LLM applications

Build reliable applications on large language models, and deploy them.

This is you

You already build software: for the web, for mobile or for the back end. You want to add large language models to real products, and you want them to work every day, not only in a demo.

Where you are going

An AI application engineer

  • Choose an LLM for a task with evidence, not hype
  • Build features on LLM APIs that handle errors, cost and bad output
  • Deploy an LLM application with an API and a database
  • Explain to your team why an AI feature behaves as it does
  • 3 stages
  • 10 courses, 10 available now
  • About 110–151 hours of study
  • 9 certificates of completion

How much code you need

  1. No code
  2. Read code
  3. Some code
  4. Code is central

Code is central, but it is code that you already know how to write. The new part is how to work with a model that does not always give the same answer.

Your route, stage by stage

Each stop is a course. Its shape tells you how much of it to take.

  • Full course. The whole course, with its practice. It leads to a certificate of completion.
  • Concepts. Only the concept modules, read without running code. They lead to a concepts certificate.
  • Optional. Useful for some people. You do not need it, and it is not counted in the time.
  1. You, today

  2. Stage 1 Foundationsabout 34–46 h

    1. AI Career Foundations: Roles, Skills and Roadmaps

      Full course4–6 h

      See where your developer skills fit in AI work.

    2. Python for Practical AI Engineering

      Full course18–24 h

      Python is the language of most AI libraries.

      Focus: If you already have these skills, do its final assignment instead.

    3. Git and Team Development Essentials

      Optional5–7 h

      You use Git every day already. Take it only if branches, reviews and merges are new to you.

    4. Essential Mathematics and Statistics for AI

      Full course12–16 h

      Only the statistics that you need to compare models and results.

      Focus: If you already studied this, do its final assignment instead.

  3. Stage 2 Large language modelsabout 30–42 h

    1. LLMs: How They Work and How to Choose One

      Full course8–12 h

      How LLMs work, and how to choose one.

    2. Building Reliable Applications with LLM APIs

      Full course22–30 h

      The core of this path: LLM features that are reliable.

  4. Stage 3 Ship itabout 46–63 h

    1. Build and Deploy Your First API

      Full course11–15 h

      Serve your feature behind an API.

      Focus: If you already have these skills, do its final assignment instead.

    2. Docker and Cloud Essentials for AI Developers

      Full course7–10 h

      Run it in a container, in the cloud.

    3. SQL and Data Preparation for AI

      Full course12–16 h

      Data for prompts, and for checking results.

    4. Databases and Storage for AI Applications

      Full course16–22 h

      Store conversations, documents and vectors.

  5. You arriveAn AI application engineer

Earn certificates as you go

You do not need to finish the whole path to show what you learned. Each full course gives a certificate of completion, and each concepts course gives a concepts certificate. Share each one when you get it.

When you are ready, prepare for the interview: Interview preparation: AI Engineer

Make it my path All learning paths

Choose this goal in your profile. My learning then shows your progress on this route, and the weeks it takes at your pace.