Week 1 free
LLMOps
An 8-week, project-based, portfolio-first program on operationalizing Large Language Models (LLMOps). Build a real LLM application, ship it publicly, and walk away with a portfolio piece, not a grade.
- Pace
- Self-paced, start any week
- Length
- 8 weeks · 45 video lessons
- Repo
- paiml/llmops-applied-program
Weekly email reminders: join the programjoin the program. Or add the 8 weeks to your calendar, starting one week from today:
Outline
Week 1 · Generative AI Concepts + Dev Environment Setup
- Choose the problem your project will solve, and who it's for
- Choose your programming stack — Python or Rust
- Set up your dev environment and initialize the project repository
- Introduction to Generative AI Members
- Public Speaking Members
- Developing Effective Technical Communication Members
- Exploring Cloud Onboarding Members
- Python Development Environments Members
- Pytest Master Class Members
- Python Essentials for MLOps: Applied Python for MLOps Members
- Rust: Setting up your Rust Development environment Members
Week 2 · Interacting with Large Language Models
- Decide how you'll interact with the SLM/LLM (direct API calls, an SDK, a local server's HTTP endpoint, etc.)
- Experiment with prompts against a model and note the failure modes your application will need to handle (bad output, timeouts, hallucination)
- Sketch the input/output contract your application expects from the model
Week 3 · Local Large Language Models
- Evaluate the local LLMs/SLMs available to you (Llamafile, Ollama, llama.cpp, etc.) against your problem
- Choose the model and serving tool for your project
- Get it running locally and confirm you can call it programmatically from your application's stack
Week 4 · Applied Solutions + Extensibility
- Build the core application logic around the model — input handling, prompt construction, output parsing, error handling
- Identify what plugins or functions would extend your application, and pick one to prototype
- Sketch an architectural overview of your application
- Local LLMOps Members
- AI Pair Programming from CodeWhisperer to Prompt Engineering Members
- Using Local LLMs from Llamafile to Whisper.cpp Members
- Open Source Platforms for MLOps: Introduction to Hugging Face Members
- Open Source Platforms for MLOps: Deploying Hugging Face Members
- Open Source Platforms for MLOps: Applied Hugging Face Members
- Extending with Functions and Plugins Members
- Applications of LLMs Members
- MLOps Platforms: Amazon SageMaker and Azure ML — Week 1 Members
Week 5 · Retrieval Augmented Generation
- Decide whether RAG fits your project — not every project needs it
- If it does, implement a basic retrieval pipeline over your document set
- If it doesn't, document why, so the decision shows up in your project's history and demo
Week 6 · Python Web Frameworks for APIs
- Choose a web framework (FastAPI, Flask, or a Rust equivalent) if your interface needs one — skip this if your interface is a CLI
- Wire the framework into your existing application logic
- Expose your application's endpoints and confirm they work end to end
- Introduction to FastAPI Framework Members
- Introduction to Flask Framework Members
- Applied Python for MLOps Members
- Cloud Virtualization, Containers and APIs Members
Week 7 · DevOps Principles + Deploying ML APIs
- Containerize the application, without baking the model into the image
- Set up GitHub Actions CI to build the container image on push
- Apply and document basic DevOps and responsible-AI practices for your project
- Responsible Generative AI Members
- Applying DevOps Principles Members
- MLOps Platforms: Amazon SageMaker and Azure ML — Week 2 Members
- MLOps Platforms: Amazon SageMaker and Azure ML — Week 3 Members
- Introduction to GitHub Actions Members
- Building an End-to-End LLM application in Azure Members
- Operations Members
Week 8 · LLM Platforms + Ship & Finalize
- Evaluate what a cloud LLM platform would change about your application, as a point of comparison to your local/self-deployed setup
- Run your project against the self-assessment checklist
- Publish the repository publicly and write a short portfolio/LinkedIn post linking to it
- Introduction to LLMOps with Azure Members
- mlflow-project-best-practices Members
- MLOps Platforms From Zero: Databricks, MLFlow/MLRun/SKLearn Members
- Azure Databricks, Pandas, and Opendatasets Members
- MLOps Platforms: Amazon SageMaker and Azure ML — Week 4 Members
- MLOps Platforms: Amazon SageMaker and Azure ML — Week 5 Members
Roles it prepares you for
- LLMOps Engineer
- MLOps Engineer
- AI Application Developer
- Machine Learning Engineer
- Platform Engineer
Skills you'll practice
- Large Language Model Integration
- Prompt Engineering
- Local LLM Deployment (Llamafile, Ollama, llama.cpp)
- Retrieval Augmented Generation (RAG)
- Python or Rust Application Development
- API Development (FastAPI/Flask)
- Containerization & CI/CD
- Responsible AI Practices
Prerequisites
Basic Linux and programming skills. All project work can be completed in either Python or Rust — you don't need both.
Questions
Is there a grade or enrollment gate?
No. There's no grading, no enrollment gate, and no required login to work through the program's repository. Joining just sets up weekly email reminders and an optional calendar schedule.
Can I run this rolling or as a cohort?
Both. Rolling/self-paced means you start whenever you want with no meetings. Cohort runs alongside a shared start date with a dedicated Discord channel and an end-of-run demo call.
Do I need to log in to use the calendar invite?
No. The calendar buttons above work without logging in, with a schedule starting one week from today.
What does membership add?
Week 1's videos are free. Membership opens every week's videos and the full course library they come from. See pricing.