Core Systems

Build a small AI application that someone else can run, evaluate, and use. Learn the engineering, modeling, and deployment skills along the way.

Start with Software Engineering for AI. Complete the five modules below, choose two electives, and deliver your integrated project.

Before you start

Complete Engineering Fundamentals or demonstrate equivalent skills through the Academy direct-entry review. You should be able to write and debug Python, use a local environment and Git, manipulate data with NumPy/Pandas, query SQL, interpret plots, and use basic linear algebra, probability, and statistics. Derivatives preparation is provided within deep learning; no prior FastAPI, Docker, PyTorch, or LLM application experience is required.

Your learning path

Module 1

Software Engineering for AI

Project structure, tests, collaboration, verified AI-assisted work

Module 2

Applied ML & Deep Learning

Evaluation, classical models, training, PyTorch, pretrained inference

Module 3

LLM Applications

Structured outputs, context, evaluation, failure handling

Module 4

Systems, Networking & Data

HTTP/DNS, Linux, SSH, troubleshooting, persistence

Module 5

APIs, Containers & Deployment

FastAPI, Docker, automated tests, deployment

How to work through the stage

Start Software Engineering for AI and keep using its habits throughout the stage. Complete Applied ML before deep learning, including the short derivatives preparation before the deep learning section. Systems can run alongside modeling work. Begin APIs and deployment after systems and a working inference function from ML, deep learning, or LLM applications.

Build the integrated project incrementally. Retain the separate ML evaluation and deep learning exercises even if the final project uses an LLM. Required exercises may share a repository with clear directories and run instructions.

Electives

Complete exactly two electives after completing their prerequisites. Use them to add a capability to your project. Further reading within a required module does not count as an elective.

Elective

Electives · Choose two

Explore 5 choices and complete two. Each section includes prerequisites, resources, practice, and completion requirements.

Choose based on a capability and a project where you can practice it. Examples: Retrieval + Agents for grounded workflows; Model Adaptation + MLOps for experimentation and delivery; Backend + MLOps for reliability. Other combinations are valid when supported by your project.

Electives introduce capabilities explored more deeply in specialization. Keep each to one defined feature, an evaluation approach, and an explanation of tradeoffs. Both electives may extend one project, but document their outcomes and evidence separately.

Finish this stage

Deliver the Integrated Project & Handover, revise it after review, and meet the completion checks. Watching tutorials alone does not establish the outcomes. Continue into specialization afterward.

Plan your study time

Use the provisional estimates where supplied. Other workloads remain pending pilot. Include implementation, debugging, review, and revision.