stackademic

The leading education platform for anyone with an interest in software development.

Learning Paths / AI Engineer Track

career
advanced
20h estimated

AI Engineer Track

A career track for AI engineers: Python, ML and LLM foundations, prompt engineering, embeddings, RAG, agents, and evaluation.

Start learning →

Python for AI

  1. 1

    Functions

    Define reusable blocks of code with parameters, returns, and defaults

  2. 2

    Classes

    Define objects with attributes, methods, inheritance, and dunder methods

  3. 3

    Async/Await

    Write concurrent I/O-bound code with coroutines, the event loop, and asyncio

  4. 4

    Type Hints

    Annotate code with static types for tooling, clarity, and safer refactors

Foundations

  1. 1

    AI Fundamentals

    Core concepts, types of AI, and essential terminology for developers

  2. 2

    Machine Learning Basics

    Supervised and unsupervised learning, training, and inference for developers

  3. 3

    Neural Networks

    Layers, weights, forward passes, and activation functions explained

  4. 4

    Large Language Models

    Transformers, tokens, context windows, and what LLMs can and cannot do

Working with LLMs

  1. 1

    Prompt Engineering

    System and user messages, few-shot examples, chain-of-thought, and practical tips

  2. 2

    Advanced Prompt Engineering

    Structured prompting, few-shot design, and reliable JSON output

  3. 3

    AI APIs

    Calling LLM APIs from code with keys, requests, and streaming

Retrieval

  1. 1

    Embeddings

    Vector representations, similarity search, and practical use cases

  2. 2

    Embeddings Deep Dive

    Distance metrics, normalization, chunking, and dimensionality tradeoffs

  3. 3

    Vector Databases

    Storing and querying embeddings for similarity search at scale

  4. 4

    RAG Basics

    Retrieval-augmented generation pipeline for developer applications

  5. 5

    Advanced RAG

    Hybrid search, reranking, query rewriting, and grounded generation

Agents & Tuning

  1. 1

    AI Agents

    Tool use, agent loops, and when agents beat simple prompts

  2. 2

    Agent Architectures

    Tool-calling loops, planning, memory, and multi-agent patterns

  3. 3

    Fine-Tuning

    When to fine-tune, data preparation, LoRA, and hosted fine-tuning APIs

Quality & Ethics

  1. 1

    Evaluation

    Building eval sets, metrics, and LLM-as-judge for reliable systems

  2. 2

    Responsible AI

    Bias, hallucinations, privacy, and human oversight for production AI