AI Bootcamp (Flagship Capstone)

AI Bootcamp (Flagship Capstone)

Duration: 10 Days

Description

The AI Bootcamp is nTier’s flagship capstone, an intensive, project-driven program that brings together the full technical curriculum. Serving as the shared capstone for both the developer and data/ML engineering tracks, it challenges participants to design and build a substantial AI system end to end: from data and retrieval through LLM application logic, agents, evaluation, and production concerns. Working on a realistic project with guidance from experienced instructors, participants consolidate their skills, fill gaps, and leave with a portfolio-worthy build and the confidence to deliver AI systems in the real world.
Class time is heavily hands-on: project work and labs (70 percent) with focused instruction, design reviews, and discussion (30 percent).

Audience

Developers and data/ML engineers who have completed the core technical courses and want a capstone experience building a complete AI system. The shared culmination of both technical tracks.

Objectives

  • Design a complete AI system from requirements to delivery
  • Integrate data, retrieval, LLM application logic, and agents
  • Apply evaluation, reliability, and security throughout
  • Address production concerns: deployment, monitoring, and cost
  • Collaborate and present technical design decisions
  • Produce a portfolio-worthy end-to-end project

Prerequisites

The Bootcamp assumes completion of the core technical curriculum or equivalent experience. Participants should bring:

  • Strong Python skills (see Python Foundations)
  • Experience building LLM applications and/or ML systems
  • Familiarity with agents, retrieval, and deployment concepts

Course Outline

  • Module 1 – Kickoff and Project Design
    • Welcome and objectives
    • Capstone project options and scoping
    • Requirements, architecture, and planning
    • Forming teams and setting up
  • Module 2 – Data and Retrieval Foundations
    • Preparing data and knowledge sources
    • Building retrieval and grounding
    • Design review and feedback
    • Project work
  • Module 3 – Application and Agent Logic
    • Building core application and workflow logic
    • Adding agent capabilities and tools
    • Integrating components
    • Project work
  • Module 4 – Evaluation, Reliability, and Security
    • Building evaluation and testing
    • Hardening for reliability and security
    • Cost and performance tuning
    • Project work and design review
  • Module 5 – Delivery and Presentation
    • Deployment and operational readiness
    • Final integration and polish
    • Presenting design decisions and results
    • Capstone presentations and wrap-up