AI Engineering Bootcamp

Module 1

• Intro to AI Engineering & Command-Line Workflows

Get acquainted with the AI engineering lifecycle and learn essential command-line tools to navigate, automate, and manage projects efficiently.

• Git Version Control

Master Git fundamentals—branching, merging, and collaborative workflows—to track changes and collaborate seamlessly on codebases.

• Python Essentials & Advanced Data Handling

Review core Python syntax and delve into file I/O, error handling, and optimized data structures for robust script development.

• NumPy & Pandas for Data Analysis

Harness NumPy arrays for numerical computing and Pandas DataFrames for cleaning, transforming, and analyzing complex datasets.

• SQL Essentials & Intermediate Queries

Learn to design relational schemas and write SQL queries for filtering, aggregating, and joining data across multiple tables.

• Object-Oriented Programming
  Apply classes, inheritance, and encapsulation to build modular, reusable code that scales with project complexity.

Tools that will be used:

Module 2

• ML Fundamentals

Explore the theory behind model training, evaluation metrics, and the bias–variance tradeoff to build accurate predictive systems.

• Supervised & Unsupervised Learning

Implement classification, regression, clustering, and dimensionality-reduction algorithms to extract insights from labeled and unlabeled data.

• Intro to Neural Networks & PyTorch

Build, train, and debug simple neural networks using PyTorch’s dynamic computation graph and tensor operations.

• CNNs & Deep Learning

Dive into convolutional architectures for image and spatial data analysis, learning best practices for deep model design and regularization.

• Reinforcement Learning

Study agents, environments, and reward signals to implement RL algorithms that learn optimal behaviors through trial and error.
 

Tools that will be used:

Module 3

• Natural Language Processing & Word Embeddings

Process and vectorize text using tokenization, stemming, and embedding techniques to prepare data for downstream tasks.

• Transformer Models

Understand attention mechanisms and build state-of-the-art encoder–decoder architectures for sequence modeling.

• Gen AI Fundamentals

Survey generative modeling approaches—VAEs, GANs, autoregressive models—and their applications in media synthesis.

• Vector Databases & Knowledge Graphs

Learn to store and query high-dimensional embeddings and structured knowledge graphs for efficient semantic search.

• Chatbot Development & AI Agents

Design conversational pipelines, integrate LLM APIs, and orchestrate AI agents to build interactive dialogue systems.

Tools that will be used:

Module 4

• APIs and API Development

Develop and deploy RESTful and GraphQL endpoints to serve ML models as production-ready microservices.

• Remote Servers & Docker

Containerize applications and manage remote Linux environments to ensure reproducible, scalable deployments.

• CI / CD Pipelines

Automate testing, building, and deployment workflows using tools like GitLab CI/CD to maintain high code quality.

• Microsoft Azure

Leverage Azure services for compute, storage, and ML ops—setting up resource groups, Kubernetes clusters, and monitoring.

Tools that will be used:

AI Challenge

Final Project

Work within a team on your final project, applying everything you have learned in practice on a real-world use case. The program finishes with the presentations of the final projects, where you receive your certification.