AI Engineer in Python

Write basic Python programs by working with variables, data types, lists, loops, and conditionals to support simple development tasks.

Structure Python programs by working with dictionaries, functions, and APIs to retrieve data, organize logic, and support larger application workflows.

Advance your Python development skills by using object-oriented programming, list comprehensions and lambda functions, decorators, regular expressions, and error handling in real projects.

Explore essential tooling specifically tailored for Python enthusiasts through practical drills that stick.

Explore how AI chatbots and large language models are reshaping communication through guided interaction, real examples, and hands-on practice.

Examine real-world applications of large language models by designing prompts, managing context, and building AI-driven workflows in Python.

Learn to build reliable LLM systems with structured outputs, function calling, and tool integration. Move beyond basic prompting to create maintainable workflows using validation, agentic loops, and the Model Context Protocol.

Explore APIs with Python to retrieve real-world data for AI-focused analysis and applications.

Build and deploy an LLM-powered API using FastAPI, Docker, and Docker Compose. From creating HTTP endpoints to running hardened, multi-container stacks.

Develop practical skills with NumPy and pandas to explore, clean, and analyze data efficiently using real datasets and guided practice.

Apply statistical reasoning to visualization by combining Python plotting tools with sound design choices to communicate patterns, trends, and insights clearly.

Practice cleaning and preparing messy datasets in Python by aggregating, reshaping, and combining data for efficient, real-world analysis.

Practice core statistical techniques in Python to sample data, analyze variables, and visualize frequency distributions for real projects.

Develop practical skills to summarize distributions, measure variability, and compare values using core statistical tools in Python.

Build a practical foundation in probability using Python, covering random experiments, core rules, and counting techniques used in data analysis.

Extend probability fundamentals to conditional reasoning, independence, and prior knowledge, culminating in a Naive Bayes spam filter.

Practice hypothesis testing in Python by running chi-square and permutation tests to evaluate real-world outcomes and statistical significance.

Develop a supervised machine learning workflow for classification by training, evaluating, and tuning models with scikit-learn on real-world datasets.

Apply unsupervised machine learning techniques by building, evaluating, and interpreting k-means models to segment and explore unlabeled data.

Explore the calculus concepts that power machine learning, from rates of change and derivatives to the mechanics behind optimization algorithms.

Build hands-on linear algebra skills for machine learning by working with vectors, matrices, and systems used in real ML models.

Model and interpret relationships between variables by constructing, evaluating, and applying linear regression for inference and prediction.

Optimize machine learning models by implementing and applying gradient descent techniques to efficiently train and improve predictive performance.

Classify and interpret categorical outcomes by constructing, evaluating, and applying logistic regression models for inference and prediction.

Apply decision trees and random forest models to solve classification and regression problems while producing interpretable, high-performing predictions.

Improve machine learning model performance by applying optimization techniques such as cross-validation, regularization, and feature engineering in Python.

Explore how PyTorch is used across major deep learning application areas including sequence models, natural language processing, and computer vision.

Learn how embeddings capture semantic meaning beyond keywords and power modern AI systems including search, RAG, and agent memory.

Learn how vector databases enable fast semantic search at scale. Build production-ready systems with ChromaDB, implement hybrid search strategies, and explore caching patterns for LLM applications.

Learn to build Retrieval-Augmented Generation (RAG) systems in Python, covering pipeline architecture, prompt design, query expansion, reranking, and debugging common failure modes.