AI Makerspace

Cohort 1

Cohort 2

LLMO4

AIE1

AIE2

LLMO3

LLMO1

LLMO2

AAIE1

AIE3

Self-paced cohort

AIE4

AIE5

Cohort 3

Cohort 4

AIE6

Cohort 7

Understand how everything comes together in the course! Key updates for the Enterprise: A focus on the importance of On-Prem solutions as the first phase in the journey of the aspiring AI Engineer or leader looking for product adoptions. However, it is only Phase I of 5 phases... Get&nbsp;all the details&nbsp;about tools we'll use and relevant papers for each project assignment, how to become AI-Makerspace Certified, and prerequisite learning pathways.

📅 Detailed Course Schedule & Curriculum - Updated for Cohort 7!

 
 

Access all of the concepts and code directly&nbsp;on <a href="https://www.youtube.com/playlist?list=PLrSHiQgy4VjGQohoAmgX9VFH52psNOu71" rel="noopener noreferrer" target="_blank">YouTube</a>&nbsp;to start building, shipping, and sharing with LLM Ops! **Note: This is from cohort 1 which we ran between August and September of 2023** <ol><li>Build complex apps with LLM Ops frameworks including LangChain and LlamaIndex.</li><li>Understand LLM product development methods, from prompting to retrieval and beyond.</li><li>Build, deploy, evaluate, and operate your own end-to-end production RAG system.</li></ol>

Learn LLM Ops for Free, Async!

Master language models and embedding models through training, fine-tuning, aligning, distilling, and merging transformer architectures! Get access to lectures, code repositories, and more!&nbsp; We highly recommend all students taking The AI Engineering Bootcamp to go through this material first! Why? It turns out that it's super helpful to understand what's happening inside of the LLM when you try to build complex applications with them. Not required, mind you, but super helpful. Get started building, shipping, and sharing for free now 👇

LLM Engineering, Cohort 3 Full Course ~ a $1999 value 

Do you want to really understand how LLMs work "under the hood," from&nbsp;concepts&nbsp;to&nbsp;code Everyone drives cars, but how many people really know how the engine works? Whether you're looking to nail AI Engineer interviews or lead an entire AI Engineering team,&nbsp;positioning yourself the LLM expert in your context is just five days away.

LLM Foundations, a FREE 5-Day Email Course

Understand how everything comes together in the course to provide a holistic overview of the how LLMs are engineered. Get all the details about the assignments, associated papers, and key concepts you'll learn!

📅 Detailed Schedule!

You’ll find brief introductions to core concepts we’ll cover in more depth in the class - this is meant to get the learning juices flowing with bite-sized training materials from Dr. Greg and The Wiz.

The LLM Engineering Onramp

Understand how everything comes together in the course to provide a holistic overview of the LLM Ops space. Get all the details about the assignments and tool stacks!

📅  Detailed Schedule!

Become an AI Engineer in the world's leading community for people who want to build, ship, and share production LLM applications 🏗️🚢🚀.

"Dr. Greg" Loughnane

Co-Founder & CEO @ AI Makerspace

Chris "The Wiz 🪄" Alexiuk

Co-Founder & CTO @ AI Makerspace

The AI Engineering Bootcamp

Customer Engineer

Fullstack Software Engineer

Data Scientist

Principal Engineer 

financial economist

Data scientist

VP Computing, Data Science, Technology 

AI Consultant

Principal AI Eng

**EXPANDED CAPACITY AND INTERNATIONAL TIME ZONES FOR COHORT 7** Section 01: Live Sessions are Tuesday/Thursday 7-9 PM Eastern Time (ET), led by Dr. Greg &amp; The WizSection 02: Live Sessions are Tuesday/Thursday 7-9 PM Central European Time (CET), let by International Instructors Let us know which section you're applying for in your application! OUR COMMUNITY🏗️ 🚢🚀 AI Makerspace is on a mission to create the world's leading community for people who want to build, ship, and share production LLM applications. Welcome! We invite you to join our close-knit AI Makerspace community on YouTube (learn live weekly with us for free at 10 AM PT on Wednesdays!) or Discord to start building, shipping, and sharing with us today! https://aimakerspace.io/ OUR COURSEThe AIE Bootcamp is truly a bootcamp. It's hard. It's a grind. But it will transform you! It will get you comfortable thriving at "The LLM Edge" and beyond. Our students don't just learn; they transform! Plus, every cohort culminates in a live Demo Day experience! Many of our graduates have launched entirely new startups based on their demo day presentations! To hear our student's stories and for a quick glance at all the tools you'll master, check out the following link now! https://aimakerspace.io/the-ai-engineering-bootcamp/ OUR ETHOSBuild 🏗️, Ship 🚢, Share 🚀! This is the secret to success in a 21st-century workforce, and you will live this every class, every week of the cohort! 🧑‍🤝‍🧑 Specifically, you will get hands-on experience building and sharing complex LLM and agentic applications weekly, receiving constant feedback during live sessions and through your homework submissions via instructors, peer supporters, and your fellow cohort members. 🙋 WHAT ARE THE PREREQUISITESYou must be familiar with Python programming, prompt engineering, and data science. However, most of all, you must be driven to succeed in Generative AI in 2025. 🙋 How will I know if it's right for me? If you're unsure if this course be a fit for you, you'll find tons of resources on this page to help you decide, including: 📜 Curriculum &amp; Detailed Schedule: https://bit.ly/aie7-curr🤩 Demo Day Videos (from cohort 5): https://bit.ly/aie5-demos🎤 Student Interview Videos: https://aimakerspace.io/category/transformations/ Here are a few long-form pieces of writing about the student experience:- Richard Gower, Cohort 3: https://bit.ly/aie-cohort-3-reflections- Ches Roldan's "20 Tips to Survive AI Makerspace’s AI Engineering Bootcamp (as a non-technical person)": https://bit.ly/aie-20tips 💰 How much do the tools cost? Don't worry! This course is for the GPU-poor among us! This course adapts to industry-standard open-source software and compute hardware and is cloud platform agnostic. We strive to keep your additional costs low (below ~$100 total). Check Q&amp;A for more info!** WHO HAS TAKEN THIS COURSESince its launch in January 2024, over 250 people have taken the course! A wide range of professionals have taken the course. A wide range of professionals took this class. Many participants were Software Engineers and Developers, reflecting a strong technical base. A significant portion were Data Scientists and Machine Learning/AI Specialists, indicating a focus on analytics, modeling, and artificial intelligence. There were also numerous Executives and Leaders (CEOs, CTOs, Directors), Product/Project/Program Managers, Consultants, and even Professors or Students. Here is a list of companies whose employees have already taken the course: Google, Meta, Microsoft, Amazon, Samsung, Salesforce, IBM, Oracle, Bloomberg, Deloitte, Atlassian, SAP, Infosys, ServiceNow, Shopify, NetApp, Autodesk, Jio Platforms, JP Morgan Chase (JPMC), Walmart, Chevron, Expedia, NTT Data, Ernst &amp; Young, Fannie Mae, National Grid, State Farm, USAA, BMO, TD Bank, Mercer, Kiewit, BP, CVS, Safran, Appian The most important thing for anyone taking the course is to take it seriously. This advanced course requires commitment, debugging, resilience, and tenacity. These personal attributes matter much more than your current company or job title. That said, software engineers and developers working in industry today have a leg up because many of the requirements (e.g., dev environment, interacting regularly with GitHub, writing code) will not seem new or foreign. WHAT STUDENTS (REALLY) SAID ABOUT COHORT 5:We collect feedback every single class. Here is an analysis of the 160 pieces of feedback that we received on the question "Is there anything else you'd like to share with us?" that we asked at the end of each of the 20 live sessions, completed by ChatGPT with the o1 model in April, 2025. Highly Positive Themes- Students repeatedly praise the instructors’ expertise and clarity.- Many love the breakout rooms, citing them as a key differentiator from other courses.- There is strong enthusiasm about practical coding sessions, community support, and peer supporters.- Several comments mention that they are already deploying real applications and seeing immediate value, which is a significant selling point for future students. Neutral or Constructive Feedback- A few suggestions for improving logistics (e.g., link consistency, environment setup, more thorough instructions).- Requests for additional examples and smaller breakout groups.- A handful of people struggled with first-class onboarding or missed classes due to personal constraints. Negative or Dissatisfied Feedback- Some frustration around external tool links (Discord, GitHub) not working seamlessly.- Occasional complaints about environment setup challenges.- A single extended critique about missing the first day and feeling lost initially, but that student did eventually get on track. We are always working to improve our product, our student experience, and our processes! You can count on the fact that we've taken the feedback into account for Cohort 6 and beyond! Here were the top 10 direct quotes: 1. “One of the best lessons I’ve ever had. The instructor’s level of expertise is high and his communication is extremely easy to understand. I have grasped all the concepts.”2. “This session was pure gold, seeing actual applications, really nice!”3. “I am having lots of fun and learning. LOVE THE ENERGY! Let’s go.”4. “The breakout rooms are absolutely fantastic. Peer Supporters are bae.”5. “The breakout rooms are just so good – easily sets it apart from 90% of other courses out there.”6. “It was a great session today. Super helpful and getting clearer. Amazing job everyone. Love this!!!!”7. “I have deployed and built a number of applications right from the first sessions of the course. Knowledge also helps me in self-study and research.”8/ “This class was worth every dollar, thank you guys!”9. “Thank you for an amazing ride! &lt;3”10. “I complained last time about the breakout rooms not being long enough and the lectures being too long. This time I think the ratio was GLORIOUS PERFECTION!”

Prototype agent apps and get them into Production. Ship fast and keep data safe.

Provide a brief description for each module as a way to sell the value of what students will be learning throughout the course.

First Module

Second Module

Third Module

Course syllabus

<ul><li>W1: June 24th, 26th</li><li>W2: July 1st, 3rd</li><li>W3: July 8th, 10th</li><li>W4: July 15th, 17th</li><li>W5: July 22nd, 24th</li><li>W6: July 29th, 31st</li><li>W7: August 5th, 7th</li><li>W8: August 12th, 14th</li><li>W9: August 19th, 21st</li><li>W10: August 26th, 28th</li></ul> * All sessions are recorded!

Tuesdays & Thursdays

Each class period, we will get hands-on with Python coding homework!

Weekly Programming Projects

Open to the public - Friends, family, coworkers, and bosses welcome! <a href="https://www.youtube.com/playlist?list=PLrSHiQgy4VjGG6wvPyIPoBnH2iqjtLY68" rel="noopener noreferrer" target="_blank">AIE5 Demo Day YouTube Playlist</a><a href="https://www.linkedin.com/events/7305318024528478208/comments/" rel="noopener noreferrer" target="_blank">AIE5 Demo Day Event</a><a href="https://www.notion.so/AIE5-Demo-Day-Run-of-Show-1b5cd547af3d805e8bb7d049413ee129" rel="noopener noreferrer" target="_blank">AIE5 Demo Day Run of Show</a>

Demo Day!

Dr. Greg: Thursdays @ 10 AM PTThe Wiz 🪄: Fridays @ 3 PM PT

Instructor Office Hours

We typically cover 6-7 days per week with 1 or more office hours held by peer supporters!

Peer Supporter Office Hours

Tuesdays at 10 AM PT: For International (EMEA) students, a Certified AI Engineer will hold weekly 60-minute deep dive sessions!

International-Friendly Weekly Deep Dive Sessions

Course schedule

Software engineers and developers who want to build complex LLM and agentic applications.

Data scientists and machine learning engineers aiming at becoming full-stack AI practitioners.

Technical product managers or execs who guide their teams on what to build, why, and how.

Who is this course for

What you’ll get out of this course

You will present a unique project live to a cohort of your peers and the public!

🤩 Demo Day!

Certified AI Engineers get direct access to job opportunities from our network

💼 Hiring Opportunities

Work with certified AI Engineers in dedicated small Journey groups to discuss and code throughout the cohort!

🧑‍🤝‍🧑 Peer-Supported Live Coding

Student success will help you achieve your goals before and after certification!

🤝 1:1 Career Coaching

Leverage in-context learning as an engineer for prototyping, RAG applications, agents, and more!

🧑‍💻 Prompt Engineering

Best-practice RAG tooling, techniques, and best-practices exist now. Learn them!

🙋 Retrieval Augmented Generation (RAG)

Build complex LLM applications capable of reasoning, action, and working with external tools!

🕴️ Agents

Efficiently fine-tune LLM and embedding models to adapt to your task or domain!

⚖️ Fine-Tuning

From o1 to agentic conversation programming, we'll cover the latest in LLM reasoning and frameworks.

🤔 Reasoning & Test-Time Compute

Instrument agent applications for metrics-driven development to show your quality improvements quantiatively.

📈 Evaluation

Debug, test, and monitor applications built using any leading LLM framework!

🔎 Observability

Learn the leading tools and quantization techniques to accelerate inference for the latency and throughput you need.

📊 Inference Optimization

Learn to efficiently leverage resources so you can keep your data super private in the years to come.

🏢 On-Prem Serving

Build hands-on with <a href="https://docs.astral.sh/uv/" rel="noopener noreferrer" target="_blank">uv</a>, <a href="https://www.cursor.com/" rel="noopener noreferrer" target="_blank">Cursor</a>, and best-practice LLMs, vector stores, agent frameworks, and more!

🧰 Latest and Greatest

🧑‍💻 Language Model Engineering refers to the evolving set of best practices for training, fine-tuning, and aligning LLMs to optimize their use and function to balance performance with efficiency. These best practices have formed the basis for the LLMs, or Large Language Models (a.k.a. Foundation Models) and Small Language Models (SLMs) of today. 🤖 Whether you’re looking at OpenAI’s GPT series, Anthropic Claude, Grok, Google Gemini, Mistral, or any other model provider, the core underlying transformer architectures are similar, as are the training and tuning methods. When chasing after high scores on LLM benchmarks or creating state-of-the-art SLMs, techniques like Model Merging and Distillation are important as well. 🏫 This course will provide you with the foundational concepts and code to train, fine-tune, and align state-of-the-art SLMs and LLMs using industry-standard and emerging approaches from the open-source edge heading into 2025. 🤓 Become the expert in your organization on all things training (pretraining, post-training), fine-tuning (supervised fine-tuning, instruction tuning, chat tuning, etc.), alignment (PPO, DPO, etc.), Small Language Models (SLMs), Model Merging, Distillation, and more!

Understand LLMs from first principles; build custom Small Language Models (SLMs)

<ul><li>LLME&nbsp;vs. MLE</li><li>Best-practice tokenization strategies</li><li>Understanding the role of embeddings</li><li>Transformers = Attention Is All You Need</li><li>Encoder/Decoder (BART-style)</li><li>Encoder only (BERT-style)</li><li>Decoder only (GPT-style)</li><li>Build encoder-decoder and decoder-only models from scratch</li></ul>

LLM Engineering Foundations

<ul><li>GPT: "Semi-supervised sequence learning"</li><li>GPT-2: "Zero-shot task transfer"</li><li>GPT-3: "In-context learning"</li><li>Understand datasets and benchmarks for training and tuning</li><li>Compare model architecture, training, scale, limitations, and impact</li><li>Implement unsupervised pretraining, supervised fine-tuning, and instruction-tuning</li></ul>

LLM Training & Fine-Tuning

<ul><li>InstructGPT: "Aligning LLMs with human intent"</li><li>Reference (supervised fine-tuned), Policy (target), and Reward models </li><li>Proximal policy optimization (PPO) algorithm</li><li>Reinforcement Learning with Human Feedback (RLHF)</li><li>Implement RLHF and RLAIF</li><li>Limitations and broader impacts</li></ul>

LLM Alignment

Class!

Dr. Greg: Thursdays @ 8 AM PTThe Wiz 🪄: Fridays @ 3 PM PT

Office Hours

Peers supporters are here to serve as your destination group; they're available for homework help, concept deep dives, and to hang out with! Find them live in class, on Discord, and even in their own dedicated weekly sessions!

Peer Support Sessions

Data scientists, researchers, or engineers experienced with classic Machine Learning who want to build custom Small Language Models (SLMs).

Product managers who need to understand the core concepts and code behind custom SLMs to effectively lead their product teams.

Stakeholders who aim to train, fine-tune, or align proprietary SLMs for their customers in 2025.

By the end of this course, you will be able to:

🦾 Build, train, and evaluate Language Models using transformer variants (GPT, BERT, BART)

🧐  Calculate self-attention and understand the latest implementations (Flash Attention, FA2)

🔠 Demystify embedding layers, embedding representations, pre-trained vs. learned embeddings, ROPE, and more!

🪙 Decode embedding space representations for optimal next-token prediction

🔡 Build, train, and evaluate embedding models (like those in 🤗 Sentence Transformers)

🚇 Complete unsupervised and continued pretraining of LLMs and SLMs from scratch

🚉 Fine-tune pre-trained LMs for instruction-following, chat, and more via parameter-efficient methods

🛤️ Align LMs to balance helpfulness with harmlessness and other criteria (RLXF, DPO)

🚀 Explore frontiers of Language Models (Mixture-of- approaches, Model Merging, alternative fine-tuning, and more!)

Master language models and embedding models through training, fine-tuning, aligning, distilling, and merging transformer architectures!

Long-Context: RAG is Dead, Long Live RAG

Co-Founder & CEO of AI Makerspace

Chris "The LLM Wizard 🪄" Alexiuk

Co-Founder & CTO of AI Makerspace

Do these two options accomplish the same goal?  How do we make performance versus cost tradeoffs between them?

Long-context LLMs vs. RAG

Evaluation for long-context LLMs is an emerging discipline.  Meet "Needle in a Haystack," "Ruler," and what's next!

How do we even know if long-context LLMs are good?

Technically, how was this done?  What goes into this computationally and what are the implications for LLM development?

How did Gradient increase Llama 3 8B from 8k context to 4M?

Multi-Agent Systems for Everyone

By combining prompt engineering, RAG, fine-tuning, and agents, we can understand multi-agent systems

Multi-agent workflows are just another pattern

When should you use multiple agents?  When do you not need to?

Single-agent vs. multi-agent use cases

Combine multi-agent collaboration with agent supervision to coordinate between pilot, copilot, and grounded operators.

Build a multi-agent pilot training simulator

Understand GenAI in 3 Key Patterns

Learn how RAG is Dense Vector Retrieval (think recommender systems) + In-Context Learning (think prompt engineering).

Retrieval Augmented Generation, or RAG

Learn how to think about efficient fine-tuning of Large Language Models (LLMs) and Embedding models!

Fine-Tuning

Understand the most popular buzzword in 2024 - Agents!  What is an agent, and how can we leverage them?

AI Makerspace

AI Makerspace

Courses

Lightning Lessons

Resources

Reviews