AI Engineering Bootcamp: Program Details

This page documents the program structure, admissions standards, instructional methodology, curriculum, assessments, capstone requirement, faculty, learning outcomes, and the credential awarded. It is the authoritative educational profile of the program.

Section 01

Program Overview

The AI Engineering Bootcamp is a one-year, full-time, cohort-based program delivered live online, structured as four 12-week terms.

Program NameAI Engineering Bootcamp
InstitutionArtificial Intelligence Institute (artificialintelligenceinstitute.org)
Program TypeFull-time professional education program (bootcamp)
Delivery FormatLive online: synchronous lectures, mentored labs, and office hours
Duration48 weeks (one academic year), organized as four 12-week terms
Weekly Commitment40 hours per week (attendance required)
Total Instructional Hours1,920 contact hours, plus assigned self-study
Cohort Start DatesSeptember (Fall cohort) and March (Spring cohort)
Cohort Size24 students per cohort
Language of InstructionEnglish
Credential AwardedCertificate of Completion with Official Transcript
Section 02

Academic Calendar

The academic year consists of four 12-week terms with a one-week break between terms. Two cohorts are admitted per year. The calendar below describes the Fall cohort; the Spring cohort follows the same structure beginning in March.

Term 1 · September – November

Engineering Foundations

Software engineering, computer science fundamentals, data structures and algorithms, databases, and developer tooling. Weekly graded assignments begin in week 1.

Term 2 · December – February

Applied LLM Engineering

Machine learning foundations, LLM APIs and prompting, embeddings and vector search, and RAG pipelines. Concludes with the midterm project and a practical coding assessment.

Term 3 · March – May

Agentic & Production Systems

LangChain and LangGraph, agentic systems, cloud deployment on AWS, CI/CD for AI pipelines, and observability and evaluation. Team projects deploy to production.

Term 4 · June – August

Advanced Architectures & Capstone

Fine-tuning, security and guardrails, system design, and distributed systems, in parallel with the capstone project. Concludes with final assessments, the capstone defense, and graduation.

Section 03

Admissions

Admission is required and selective. The process evaluates programming readiness, mathematical preparation, and the applicant's capacity for a full-time, one-year course of study. Applications are reviewed on a rolling basis until each cohort of 24 is filled.

Stage 1

Application Review

A written application documenting prior programming experience, educational background, and a statement of purpose. Faculty review every application individually.

Stage 2

Coding Assessment

A timed, practical coding assessment in Python covering control flow, functions, core data structures, and problem decomposition. A preparation guide with representative exercises is provided to all applicants.

Stage 3

Technical Interview

A live technical interview with a member of the faculty, consisting of a pair-programming exercise and a structured discussion of goals, prior work, and readiness for the program's attendance requirements.

Prerequisites

Section 04

Educational Structure

Instruction is full-time, cohort-based, and instructor-led. Each week combines live lectures, mentored labs, pair programming, team-based learning, and assigned self-study. Attendance is required and recorded as part of the academic record.

Live Lectures

Daily instructor-led lectures introducing each module's learning objectives, followed by guided implementation sessions.

Mentored Labs

Afternoon lab blocks in which students apply lecture material to graded exercises with teaching assistants and industry mentors present.

Pair Programming

Structured pairing rotations across the cohort, mirroring professional engineering practice and building code-review fluency.

Office Hours

Scheduled weekly office hours with instructors and teaching assistants for individual technical support and feedback review.

Team-Based Learning

Recurring team projects with defined roles, sprint structure, and retrospectives, finishing with the team-built capstone.

Self-Study Requirements

Assigned readings, documentation study, and practice problems form part of the 40-hour weekly commitment and are reflected in weekly assessments.

Section 05

Curriculum

The curriculum is organized into four terms of required coursework. Each module publishes learning objectives and is assessed through graded assignments and practical coding assessments. There are no electives; every graduate completes the full sequence.

Term 1: Engineering Foundations

Weeks 1–12 · 480 contact hours
AIE 101

Python & Software Engineering

  • Python
  • Python Environment for AI
  • Testing
  • Debugging
  • Code Review Practice
AIE 102

Computer Science Fundamentals

  • Data Structures
  • Algorithms
  • Complexity Analysis
  • Problem Decomposition
AIE 103

Databases, APIs & Backend Development

  • SQL & Databases
  • REST APIs
  • Backend Development
  • API Key Management
  • Security Fundamentals
AIE 104

Developer Tooling & Systems

  • Linux
  • Git
  • Docker
  • Shell Scripting
  • First LLM Calls

Term 2: Applied LLM Engineering

Weeks 13–24 · 480 contact hours
AIE 201

Machine Learning & Deep Learning Foundations

  • Machine Learning
  • Deep Learning
  • Model Evaluation
  • Transformer Architecture
AIE 202

LLM APIs & Prompting

  • OpenAI SDK Integration
  • Prompt Engineering Patterns
  • Parameter Tuning
  • Streaming Responses
  • Structured Outputs
AIE 203

Embeddings & Vector Search

  • Text Embedding Models
  • Vector Database Setup (Qdrant)
  • Similarity Search
  • Hybrid Search Strategies
  • Index Tuning & Performance
AIE 204

RAG Pipelines

  • Chunking Strategies
  • Document Parsing
  • Naive RAG Implementation
  • Advanced RAG (HyDE Re-rank)
  • Multi-Modal RAG

Term 3: Agentic & Production Systems

Weeks 25–36 · 480 contact hours
AIE 301

LangChain & LangGraph

  • Chains, Prompts & Memory
  • Tool Use & Function Calling
  • State Graphs with LangGraph
  • Human-in-the-Loop
  • Multi-Agent Orchestration
AIE 302

Agentic Systems

  • ReAct Agent Pattern
  • Tool-Using Autonomous Agents
  • Planning & Decomposition
  • Reflection & Self-Correction
  • Handling Infinite Loops
AIE 303

Production & Deployment

  • AWS Deployment (ECS / Lambda)
  • API Design for LLM Apps
  • Rate Limiting & Throttling
  • Semantic Caching
  • CI/CD for AI Pipelines
  • Kubernetes
AIE 304

Observability & Evaluation

  • LLM Tracing (LangSmith)
  • Automated Evaluation
  • Token & Cost Monitoring
  • A/B Testing LLM Configs
  • AI Evaluation Methods

Term 4: Advanced Architectures & Capstone

Weeks 37–48 · 480 contact hours
AIE 401

Advanced Architectures

  • Fine-Tuning with LoRA
  • Custom Knowledge Bases
  • Security & Guardrails
  • On-Premise LLM Deployment
AIE 402

System Design & Distributed Systems

  • System Design
  • Distributed Systems
  • Cloud Computing
  • MLOps
  • Production AI Systems
AIE 490

Capstone Project

  • Production AI System
  • Team Collaboration
  • Architecture Review
  • Technical Presentation
  • Final Demonstration
AIE 495

Career & Professional Practice

  • Technical Communication
  • Interview Preparation
  • Portfolio Review
  • Open Source Contribution
Section 06

Assessments & Academic Standards

Assessment is competency-based and continuous. Every assignment is graded, and grades are recorded on the official transcript. Students must maintain passing performance in each term to advance to the next.

Weekly Assignments

Graded coursework submitted every week, combining AI-graded automated checks with human instructor feedback on code quality and design.

Practical Coding Assessments

Timed, hands-on assessments at the midpoint and end of each term, evaluating applied competency rather than recall.

AI Technical Evaluations

Automated evaluation harnesses measure the correctness, performance, and cost-efficiency of students' AI systems against published rubrics.

Peer Review

Structured human peer reviews of pull requests each week, graded for review quality and technical communication.

Midterm Project

An individually built, end-to-end LLM application at the end of Term 2, assessed by faculty against the published rubric.

Final Assessments

Term 4 concludes with comprehensive practical assessments and the capstone defense before a faculty review panel.

Section 07

Projects & Portfolio Requirements

Graduation requires a documented portfolio of working software. Portfolio review is part of the final assessment, and every listed item below is required, not optional.

Section 08

Capstone Requirement

The capstone is an industry-scale production AI system, built by teams of three to four students over the final 12 weeks under faculty and industry-mentor supervision. Capstone completion is a graduation requirement.

Production AI System

A deployed, working system serving real usage, with authentication, observability, evaluation pipelines, guardrails, and documented operating costs.

Architecture Review

A formal design document and architecture review with faculty at the project midpoint, mirroring industry engineering practice.

Technical Presentation & Defense

A recorded final demonstration and technical defense before a review panel of faculty and industry engineers, graded against a published rubric.

Section 09

Faculty & Mentors

All instruction is delivered by practicing engineers. The teaching staff is led by a Program Director responsible for academic standards, the syllabus, and graduation requirements.

Core Faculty

Senior software engineers, AI engineers, and staff engineers with production experience building and operating AI systems.

Teaching Assistants

Program alumni and practicing engineers who staff mentored labs and office hours at a low student-to-staff ratio.

Guest Lecturers & Industry Mentors

Engineering managers and specialists who deliver guest lectures and mentor capstone teams through architecture reviews.

Christiam Ipanaque, AI Engineer & Instructor

6+ years of production experience building RAG pipelines, LangGraph agents, and enterprise AI systems. Instructs AIE 202, 204, 301, 302, 303, and 304. Full profile →

Section 10

Student Support

Support services run for the full academic year and continue through the first six months after graduation.

Section 11

Learning Outcomes

Graduates of the AI Engineering Bootcamp demonstrate competency in each of the following areas. Every outcome is assessed through graded coursework and evidenced in the graduate's portfolio and transcript.

Section 12

Credential Awarded & Graduation Requirements

Students who complete all required coursework, maintain attendance requirements, pass all practical assessments, and complete the capstone are awarded the program credential at graduation.

The Credential Includes

  • Certificate of Completion: AI Engineering Bootcamp, Artificial Intelligence Institute.
  • Official transcript: a graded academic record of all modules, assessments, and projects.
  • Digital credential: a verifiable credential suitable for LinkedIn and résumés.
  • Capstone record: documentation of the capstone system, architecture review, and defense.
  • Graduation date: recorded on the certificate and transcript.

Graduation Requirements

  • Passing grades in all sixteen required modules (AIE 101 – AIE 495).
  • Attendance in accordance with the Student Handbook and Code of Conduct.
  • Completion of all portfolio requirements listed in Section 07.
  • Successful capstone defense before the faculty review panel.

Employers and recruiters may verify any graduate's credential and request the official transcript by contacting join@artificialintelligenceinstitute.org.

Applications Are Reviewed on a Rolling Basis

Cohorts begin in September and March and are limited to 24 students. Contact the admissions office to begin your application or to request the full syllabus.