Mydra logo
Log in
>All courses>Artificial Intelligence
Artificial Intelligence
Maven logo

Maven

AI Engineering Bootcamp

  • up to 10 weeks
  • Advanced
  • Cohort-based

The AI Engineering Bootcamp is a 10-week cohort-based program designed to equip learners with the skills to build, deploy, and monitor LLM applications. Participants will gain hands-on experience with industry-leading tools and techniques, culminating in a live Demo Day presentation.

  • Generative AI
  • LLM Application Development
  • Cloud Computing
  • Python Programming
  • Data Retrieval and Augmentation

Overview

In this comprehensive bootcamp, you will learn to prototype LLM applications using best practices and the four primary patterns of Generative AI. The course covers prompt engineering, retrieval augmented generation, fine-tuning, and agent development. You'll build applications from quick prototypes to scalable production systems, using open-source LLMs and embedding models. The program also includes visibility and monitoring tools, ensuring you can evaluate and optimize your applications effectively.

  • Web Streamline Icon: https://streamlinehq.com
    Online
    course location
  • Layers 1 Streamline Icon: https://streamlinehq.com
    English
    course language
  • Professional Certification
    upon course completion
  • Full-time
    course format
  • Live classes
    delivered online

Who is this course for?

Data Scientists and Machine Learning Engineers

Aiming at becoming full-stack AI practitioners.

Software Engineers

Who want to build complex LLM applications.

Technical Product Managers

Who guide their teams on what to build, why, and how.

Join the AI Engineering Bootcamp to master the skills needed to build and deploy advanced LLM applications. Ideal for data scientists, software engineers, and technical product managers, this course will enhance your career prospects and help you achieve your professional goals.

Pre-Requisites

1 / 3

  • Complete THE AI ENGINEERING BOOTCAMP CHALLENGE.

  • Set up your LLM application development environment.

  • Deploy your first LLM application.

What will you learn?

Week 1: Prompt Engineering, LLM APIs, and Your First GPT
Learn the basics of prompt engineering and LLM APIs, and create your first GPT application.
Week 1: Embeddings and Your First RAG Applications
Understand embeddings and develop your first Retrieval Augmented Generation applications.
Week 2: End-to-End RAG Deployment
Deploy RAG applications from start to finish, ensuring production readiness.
Week 2: Production-Grade RAG with LangChain
Build production-grade RAG applications using the LangChain framework.
Week 3: Your First Agent Application with LangGraph
Develop your first agent application using LangGraph, focusing on reasoning and action.
Week 3: Multi-Agent Applications
Create applications with multiple agents working together to solve complex tasks.
Week 4: Synthetic Data Generation
Generate synthetic data to enhance your LLM applications and improve performance.
Week 4: RAG Evaluation
Evaluate your RAG applications using quantitative metrics and feedback.
Week 5: Fine-Tuning Embedding Models
Fine-tune embedding models to adapt them to your specific domain and data.
Week 5: Fine-Tuning Open-Source LLMs with Low-Rank Adaption
Learn techniques for fine-tuning open-source LLMs, including Low-Rank Adaption.
Week 6: Midterm and AIE Industry Use Cases
Participate in a midterm assessment and explore industry use cases for AI Engineering.
Week 7: Advanced Prompt Engineering
Delve into advanced techniques for prompt engineering to optimize LLM performance.
Week 7: Advanced RAG
Explore advanced concepts in Retrieval Augmented Generation for complex applications.
Week 8: Production-Ready Optimization Strategies
Implement strategies to optimize your applications for production environments.
Week 8: Deploying Scalable Open-Source Endpoints for RAG
Deploy scalable endpoints for RAG applications using open-source tools.
Week 9: On-Premise Agentic RAG
Develop on-premise RAG applications with agentic capabilities.
Week 9: Inference, Serving and GPU Optimization
Optimize inference and serving processes, focusing on GPU utilization.
Week 10: Demo Day Dress Rehearsal
Prepare for Demo Day with a dress rehearsal, refining your presentation skills.
Week 10: Demo Day
Present your final project to peers and the public, showcasing your learning outcomes.

What learners say about this course

  • “Hands down one of the best AI programs out there and truly one of the few that shows you how to *actually build* an AI-native product.”

    Peter

    VP of Product

  • “You'll find a supportive network of individuals dedicated to building, innovating, and sharing groundbreaking work.”

    Sahar

  • “Great boot camp. Alot of great information is packaged up and presented clearly.”

    Mike

    Senior Consultant

Meet your instructors

  • Dr. Greg Loughnane

    Co-Founder & CEO, AI Makerspace

    In 2023, we created the LLM Engineering: The Foundations and LLM Ops: LLMs in Production courses on Maven. Previously, I worked as an AI product manager, university professor, data science consultant, AI startup advisor, and ML researcher.

  • Chris Alexiuk

    Co-Founder & CTO, AI Makerspace

    In 2023, we created the LLM Engineering: The Foundations and LLM Ops: LLMs in Production courses on Maven. During the day, I work as a Developer Advocate for NVIDIA.

Upcoming cohorts

  • Dates

    Jul 1 — Sep 4, 2026

  • Dates

    Sep 23 — Dec 4, 2026

$3,999