Course Description:
This course explores the design, deployment, and optimization of AI infrastructure for high-performance workloads. Students will learn how to manage local and cloud-based large language model (LLM) deployments, implement cost-saving strategies, ensure security, and set up robust hardware and software environments for AI systems.

Lecture 1: Local vs Cloud LLM Deployment
Learn how to deploy LLMs both locally and in the cloud, comparing tools, costs, and privacy considerations. This session covers Ollama, Hugging Face, and best practices for balancing performance with efficiency.

Key Objectives:

• Ollama: Local model hosting and management
• Hugging Face: Model selection and fine-tuning
• Cost optimization strategies
• Privacy and security considerations

Lecture 2: AI Infrastructure Design
Understand the hardware and software design choices that impact AI performance and scalability. Explore cloud providers, on-site setups, and DevOps practices for streamlined deployment.

Key Objectives:

• Hardware requirements for different workloads
• Cloud provider comparison (AWS, Azure, GCP) 
• Dockerization
• On-site hardware