AI Engineer Bootcamp 2026: LLMs, RAG, AI Agents & Vector DBs

Set up your development environment by installing Python on Windows and Mac, installing and configuring Visual Studio Code, and adding essential extensions to be ready for coding in this course.

Install Python on Windows by downloading from python.org, running the installer with admin privileges, adding python.exe to path, and verifying installation in the command prompt with a hello world example.

Install a newer Python on Mac by downloading from Python.org, then verify with Python 3, enter the Python shell, and run simple commands like hello world and two times six.

Install Visual Studio Code, the lightweight integrated development environment for Python, to edit your code. Download the Windows, Mac, or Linux version and start coding.

Install the Python extension pack in VS code to boost your development experience, as it bundles seven extensions that streamline Python work and learning.

Set up a python project in VS Code, create app.py, write hello world with the print function, and run it from the built-in terminal.

Explore Python fundamentals as the lingua franca for machine learning, deep learning, and AI development, with a deep dive introduction and overview before tackling AI modules.

Explore how Python's readability and versatility power web development with frameworks like Django and Flask, data science, AI and machine learning, scientific computing, finance, and education.

Python is both compiled and interpreted, with the compiler producing bytecode that the Python virtual machine interprets to run code like app.py.

Declare and assign Python variables by naming them and storing string values. Print variables to display results and use error messages and memory references to debug issues.

Explore Python data types with a focus on strings. Learn how to declare strings with single or double quotes, call string methods like upper, lower, and title, and print results.

Master Python string handling by using the strip method to remove leading and trailing whitespace and building dynamic messages with f-strings that embed variables for flexible concatenation.

Learn to represent numbers in programming with integers and floats, perform arithmetic, and use Python comments, noting that comments are ignored by the compiler; replace sum with total.

Explore Python lists as ordered, heterogeneous collections and learn to access, modify, and manage items through zero-based indexing, append, remove, and pop methods using practical fruit examples.

Learn to use f-strings to pull values from a list of different types and build messages. Explore indexing list items and format outputs with string methods like .title().

Sort lists of numbers or strings in ascending order and print before and after. Learn to reverse lists, access indices safely, and use len to measure list length.

Master how to automate tasks by iterating lists with for loops in Python, print each item, and manage indentation to differentiate inside and outside the loop.

Apply Python for loops and the range function to build numeric lists, append values, and print the final list outside the loop, understanding end-exclusive ranges.

Learn to use Python's built-in functions to analyze a list of numbers: compute max, min, and sum, and print results alongside the list for verification.

Generate a list of even numbers from 0 to 100 using range with a step of 2, built with the list class.

Organize your Python projects by splitting code from the main App.py into smaller, separate files, using concrete examples like even numbers with lists and for loops to avoid screen clutter.

Demonstrate list comprehension in Python by replacing a loop that appends to a list to create squares from range(0,10) with a single line that builds and prints the list.

Explore tuples as immutable lists defined with parentheses, not square brackets. Learn to loop and access elements without modification, and recognize the error when attempting item assignment.

Explore branching in programming by using if statements and booleans to execute code based on true or false conditions, with examples like weather checks and age comparisons and else branches.

Explore Python's multi-branch logic using elif, else, and the in keyword to evaluate conditions, such as temperature thresholds like 45 and 60, and list membership.

Explore using and and or in if statements to match activities with group interests, building a simple decision engine that picks museum, pool, or picnic based on membership tests.

Learn the basics of logical operators and, or, and not, and how they evaluate expressions to true or false, with not reversing the result.

Practice checking inequalities in Python using the not equal operator, such as age not equal to 23 and toppings not equal to mangos.

Explore nested if statements on saturday to decide breakfast based on fridge contents, using inner and outer if statements to print hearty breakfast or cereal.

Explore how Python dictionaries store data as key-value pairs, declare them with curly braces, access values using keys or the get method, and handle missing keys gracefully.

Learn to modify a dictionary by adding keys and values, updating entries like email and age, and removing or clearing items with del, pop, pop item, and clear.

Learn to iterate through a dictionary using for loops to access keys, values, and items, and print or format results with f-strings.

Explore working with nested dictionaries and looping through them using for loops and f-strings to extract and display each person’s name and age from a family dictionary.

Loop through a dictionary that contains lists by using nested loops to access speakers and their topics, printing each speaker's name and topics.

Prompt users for name and age using Python's input function, capture as strings, convert to integers with int(), and illustrate arithmetic, type handling, and f-strings, including while loops.

Prompt users to enter a number, convert the input to an integer, and use the modulo operator to check even or odd, then print the result in Python.

Explore how a while loop runs while a condition is true, incrementing a counter and using break to quit, with user input to end the program.

Build an interactive quiz game that presents questions from a dictionary, accepts user answers, checks correctness, and updates the score, then displays the final score when finished or quit.

Use a while loop to remove all instances of a specific value from a list, demonstrated by removing avocado items from an ingredients list and showing the before and after.

Build a Python dream travel itinerary tool that uses a while loop to fill a dictionary with country keys and optional notes from user input, then display the itinerary.

Understand how Python functions encapsulate code blocks, declared with def, called with parentheses, and reused to perform repeated tasks, including while and for loops.

Learn how to pass data to functions using parameters, call them with arguments, and create flexible greetings by passing names and ages.

Master the order of positional and named arguments in function calls, and use named parameters like name and age to ensure coherent, readable python code.

Learn to define functions with default parameter values and use keyword arguments to provide fallbacks when inputs are omitted, illustrated by a car detail example.

See how a function uses return to output a formatted full name by combining first name and last name, applying title casing for display.

Define and test a multiply function that takes two integers and returns their product, and illustrate using docstrings with triple quotes to document arguments, return types, and descriptions.

Pass a list as a parameter to a function, loop through the plants, and print 'watering the <plant>' for each item using an f-string.

Learn to pass an arbitrary number of Python arguments with *args and **kwargs, and build a profile function that collects name and user info into a dictionary.

Learn how to organize Python code by creating modules and importing whole modules. Explore importing specific functions with from, using an arithmetic module with add and subtract.

Learn to alias imported modules with the as keyword to rename modules for simpler access. Use the alias to call module functions, as shown with a math alias in code.

Understand how object oriented programming uses classes as blueprints to instantiate objects with attributes and methods, demonstrated by a Python book example using self.

Learn how to add more methods to a class, implement describe book and read book using an f string to display title, author, and genre.

Set a default value for an attribute such as self.num_pages, then define a function to retrieve and print the book's 230 pages using an f-string.

Learn how to modify a mutable class attribute directly or through a dedicated method, using self to update num pages and keep the code concise and reliable.

Explore inheritance in object oriented programming by deriving child ebook from a parent class. Implement Python inheritance with super init and add attributes like file size and format for download.

Override parent methods to give a child class its own behavior while leveraging the superclass with super, describing and reading a book on an e-reader versus a physical book.

Learn how to create a module for your classes, import it cleanly, and instantiate objects like a book with title, author, and genre, while choosing specific imports over star imports.

Explore the Python object class as the root of the class hierarchy, and learn how default behaviors and magic methods like __init__ and __str__ shape all objects.

Explore the Python standard library, a collection of modules you can import to solve common tasks. Learn how to leverage modules such as os, pathlib, json, sqlite3, and random.

Explore the Python random module by generating random numbers with rand int and selecting random items from a list, while handling index bounds and avoiding out-of-range errors.

Learn to generate a random fruit with Python's random module by using choice instead of rand int, handle empty fruit lists, and output the result via an f-string.

Explore the date time module to manipulate dates and times, obtain current date time with now, add days via time delta, and format results with f-strings and custom formats.

Explore Python's file reading and writing capabilities, leverage modules for automation and data manipulation, and apply concepts to accomplish useful tasks efficiently.

Learn to use the path class in Python to read a text file, determine current and working directories, obtain absolute paths, and process contents with simple transformations like lowercasing.

Learn to resolve file paths using the path class to read a text file from a subdirectory, starting at the current directory with forward slashes.

Explore the Path class and its properties and methods, including read text, stem, suffix, and name, to inspect files and read content after confirming the path exists.

Write text to a file using a path, overwrite or append content, and insert new lines in a test.txt example.

Utilize the with context manager to read and write files by opening a path with the open method, using r and w modes, ensuring resources are released.

Handle exceptions in Python by using try, except, and finally blocks to gracefully manage errors such as division by zero and ensure proper cleanup.

Master the handling of file not found and index error exceptions in Python by using try-except blocks, reading files, and printing concise error messages.

Create and handle custom exceptions in Python by defining a base exception, subclassing specific errors, raising them with messages, and catching them with try/except to control program flow.

Learn to read and write JSON files in Python using the json module. Serialize dictionaries and lists with json.dumps and deserialize with json.loads, plus file handling.

Learn to collect user-entered country names and save them to countries.json, then read and display them. Implement Python functions for saving and reading JSON with a main program loop.

learn to build a simple python automation that organizes downloads into folders by file extension using the os module and a file operations module, creating directories and moving files accordingly.

Discover how to use Python virtual environments to isolate project dependencies, prevent global conflicts, and manage different Python versions by creating, activating, and deactivating per project environments.

Create and activate a Python virtual environment with venv on Windows or macOS, then install packages with pip, demonstrated by installing requests and making a simple web request.

Develop a Python-based watermarker tool that automatically scans a folder of photos and applies a watermark, such as a Vinci Bits brand mark, to each image.

Learn to install Pillow via the python package index and build a python script that adds text watermarks to images using a font and input and output folders.

Learn to add watermarks to images with python by calculating bottom-right coordinates using a 100-pixel margin, drawing white text, and saving watermarked images to an output directory.

Parse a csv file in Python using the csv module, read lines with pathlib, extract the header row, and prepare data to plot on a graph.

Identify and enumerate csv headers to map exact column positions, then extract data by index using Python's enumerate in a loop.

Extract data from a csv column by iterating rows with a reader, using the column index to pull values, append them to a temps list, and print the results.

Plot temperatures over time by loading a CSV, extracting dates and temps, formatting dates with date time, and rendering a matplotlib line graph with labeled axes and rotated date ticks.

Dive into the fundamentals of deep learning and machine learning, exploring neural networks, data handling, feature extraction, preprocessing, and the model life cycle from training to deployment.

End-to-end learning enables direct input-to-output mapping in deep networks, automating feature learning within a hierarchical structure and eliminating manual feature engineering.

Explore deep learning with neural networks, from input to output layers, through hidden layers, activation functions, and backpropagation, using bakery and restaurant analogies to illustrate training, weights, and bias.

Explain the single neuron computation: sum of inputs, weights, and bias, then apply the activation function to produce the output.

Use a restaurant analogy to explain weights in neural networks: adjust recipe proportions based on customer feedback, evolving from base stock and base seasoning to a new standard.

Explore activation functions as quality checks in neural networks, comparing ReLU, sigmoid, and softmax, and map weights, biases, and activations to restaurant steps for deeper intuition.

Explore deep learning foundations by detailing neural networks with input, hidden, and output layers, weights, biases, and activation functions, and explain how layered representations enable pattern recognition, classification, and prediction.

Compare machine learning and deep learning, clarifying how DL is a subset of ML and highlight supervised, unsupervised, and reinforcement learning, feature engineering, and NLP basics.

Compare supervised learning, unsupervised learning, and reinforcement learning with flashcards, puzzles, and dog training; contrast machine learning vs deep learning applications like fraud detection, image recognition, and natural language.

Compare deep learning, machine learning, and AI, highlighting neural networks, pattern recognition, and general problem solving. Use the kitchen analogy to map layers from DL to AI and generative AI.

Explore the fundamentals of generative AI and its architecture, including prompts, pipelines, and foundation models. See how large language models, diffusion models, and transformers enable text, image, and code generation.

Gen AI delivers text-to-text, text-to-image, text-to-code, and text-to-audio generation, built on transformers, diffusion, and gains, and operates through an iterative process with hallucination, bias, and ethics as challenges.

Explore the key components of gen ai, including generation, sampling, output filtering, and the architecture of transformers with attention, plus training approaches like fine tuning and self-supervision.

Explore the fundamentals of AI and large language models, including how they work, tokenization, data training, and building a product with LLMs through hands-on practice.

Explore how the transformer architecture powers modern language models by using encoders, decoders, and self-attention to capture long-range dependencies in text, via tokenization and embeddings.

Explore how self-attention in the transformer uses query, key, and value. Learn how attention scores produce a contextual representation by weighting related words.

Explore the transformers library by Hugging Face, a modular toolkit for state-of-the-art transformer models with tokenizers, configurations, and pipelines for text generation, summarization, classification, and question answering.

Set up a virtual environment, install transformers and torch, and build a simple llm using a distill GPT-2 pipeline with a prompt.

Explore hands-on enhancement of transformers to build and test a simple large language model. Generate text with sampling, adjust temperature, and explore tokenization, encoding, and GPT-2 demos.

Open-source models offer transparency, customization, and community collaboration with cost control, while closed-source models provide reliability and enterprise features; choose based on budget, privacy, and technical resources.

Set up your OpenAI account and API key, run your first API call with basic prompt testing, and monitor costs via the dashboard.

Discover how APIs and API keys unlock access to cloud-based language models, enabling fast, scalable AI development with HTTP requests and GPT-4, and easy workflow integration.

Learn to set up OpenAI access, authenticate with an API key, install the OpenAI Python package, manage keys with a .env file, and call GPT models via a Python client.

Learn the art and science of prompt engineering to design clear, context-rich prompts that maximize large language model performance and steer inputs toward accurate, targeted outputs.

Learn how prompt engineering boosts output quality, reduces ambiguity, and enables control by crafting, testing, and refining prompts across direct, open-ended, instructional, rule-based, and chain-of-thought types.

Explore hands-on prompting by building a prompt-grounded conversation with system and user roles, selecting a working model like GPT-4, and experimenting with prompt types to guide the model.

Master advanced prompting for large language models, including few-shot, zero-shot, chain-of-thought, and role prompts with temperature and top-p, plus reusable templates and tools like LangChain and OpenAI playground.

Engage in hands-on coding to implement few-shot prompting with an OpenAI chat model, using environment variables and a translation example to craft effective prompts.

Master zero-shot prompting by presenting direct prompts without examples. Practice asking straightforward questions to a model like GPT-4 and observe instant responses, such as the capital of France.

Explore chain-of-thought prompting by guiding the model to solve a math problem step by step, using keyword prompts and breaking tasks into smaller steps for practical LLM applications.

Explore hands-on instructional prompting techniques to ground AI models, mix prompt styles, and generate structured outputs with bullet points and markdown formatting.

Learn how temperature and top-p sampling govern randomness and output diversity in LLMs, why use one but not both, and practical tuning tips for creative vs deterministic results.

Learn to combine prompting techniques—instructional prompts, step-by-step itineraries, and chain-of-thought reasoning—control temperature and enable streaming outputs for real-time content.

Master prompt engineering to unlock the full potential of large language models, craft accurate, context-aware prompts, and generate concise, creative outputs with hands-on practice.