⬅️ Previous Readiness for LLM Engineering

By now, you know what this program is about — mastering the full lifecycle of large language models.
This lesson shows you how it all fits together: your 9-week roadmap from foundation to deployment, with two modules and two portfolio-grade projects leading to certification.

Watch This First

The video walks through each module, explains the weekly flow, and shows how the capstone projects connect to your certification goals.

Program Structure

The program is divided into two modules — the first focuses on fine-tuning large language models, and the second on deployment and production-grade engineering.

Module 1: LLM Fine-Tuning & Optimization

You’ll learn to adapt open-source foundation models for specific domains using Hugging Face, DeepSpeed, and Axolotl.
This module covers dataset preparation, parameter-efficient training, evaluation, and optimization.
By the end, you’ll complete a fine-tuned model with an evaluation report and quantized weights.

Module 2: LLM Deployment & Production Engineering

You’ll learn how to deploy, monitor, and maintain models on platforms like SageMaker, Bedrock, and vLLM.
This module focuses on inference, scalability, cost-performance tradeoffs, and production best practices.

Each module concludes with a capstone project that contributes to your certification.

Your 9-Week Learning Path

Here is the detailed schedule for the program:

Week	Focus Area	Key Themes
1	Introduction to LLM Engineering	Model types, use cases, and fine-tuning motivations.
2	Fine-Tuning Building Blocks	Tokenization, dataset prep, LoRA/QLoRA training.
3	Fine-Tuning in Practice	Full training runs using Hugging Face, Axolotl, DeepSpeed.
4	Evaluation & Optimization	lm-eval, model merging, quantization, and versioning.
5	Module 1 Capstone Project	Deliver a fine-tuned, evaluated, quantized model.
6	AWS Foundations	SageMaker training, Bedrock customization, and cost control.
7	Inference & Deployment	Deploy models using vLLM, Modal, or AWS endpoints.
8	LLM Ops & Reliability	Monitoring, observability, security, and governance.
9	Module 2 Capstone Project	Deploy a production-ready endpoint with monitoring.

Learn at Your Own Pace

This program is self-paced — the week numbers are a suggested order, not deadlines.
Move faster, slower, or jump around based on what you already know.
Your progress depends only on completing both projects and meeting the certification rubric.

Weeks are learning stages, not fixed timelines.
You decide how deep to go and when to move forward.

Tools You’ll Work With

You’ll gain hands-on experience with the same tools modern AI teams rely on:

Hugging Face for model training and management
DeepSpeed for multi-GPU optimization
Axolotl for reproducible fine-tuning workflows
Bitsandbytes / GGUF for quantization
vLLM for efficient inference
AWS SageMaker & Bedrock for deployment and scaling
Modal for serverless deployment
LangSmith & CloudWatch for monitoring and observability
Giskard for bias and safety checks

Capstone Projects

Everything you learn leads to two major deliverables:

Capstone 1: Fine-tune and optimize a model for a defined task.
Capstone 2: Deploy that model as a live endpoint with monitoring and documentation.

These projects form your professional portfolio and are the basis for certification.

Final Note

This roadmap is meant to help you build real, hands-on capability — not just theoretical understanding.
As you move through the lessons, you’ll learn to fine-tune, evaluate, and deploy large language models using the same tools production teams use every day.

When you’re ready, continue to Module 1: LLM Fine-Tuning & Optimization to begin your first phase of hands-on work.

🏠 Home - All Lessons
➡️ Next - How to Succeed in This Program

LLM Engineering Curriculum: Complete Roadmap to Fine-Tuning and Deployment