LLM Engineering Bootcamp
Deconstruct. Fine-Tune. Deploy. — A 2-Day Hands-On Bootcamp covering Architecture, SFT, RL, and vLLM.
Bootcamp Highlights
LLM Architecture
Understand transformer internals, attention mechanisms, and how modern LLMs are built from the ground up.
Supervised Fine-Tuning
Learn SFT techniques to adapt pre-trained models for domain-specific tasks with your own datasets.
Reinforcement Learning
Explore RL-based alignment with GRPO and how to steer model behavior post-training.
Production Deployment
Deploy and serve LLMs at scale using vLLM for high-throughput, low-latency inference.
Bootcamp Schedule
A 2-day intensive program taking you from LLM fundamentals to hands-on deployment.
Intro to GenAI and LLMs
Overview of Generative AI landscape, key milestones, and an introduction to Large Language Models.
How LLMs Work from the Inside
Deep dive into transformer architecture, tokenization, attention mechanisms, and training paradigms.
How to Load and Use LLMs
Hands-on lab: Loading pre-trained models, running inference, prompt engineering best practices.
Supervised Fine-Tuning (SFT)
Fine-tuning LLMs on custom datasets. LoRA, QLoRA, and efficient adaptation techniques.
Running LLMs using vLLM
High-performance inference serving with vLLM. PagedAttention, continuous batching, and deployment patterns.
RL and GRPO
Reinforcement Learning from Human Feedback, GRPO alignment, and steering model behavior.
Featured Speakers
Moaz Eldegwy
AI/ML Engineer & Educator
"From foundations to deployment — mastering the full LLM lifecycle."
Ready to Build with LLMs?
Register for the bootcamp and learn to deconstruct, fine-tune, and deploy Large Language Models.
Limited Seats Available