AI Engineering with Modal

Welcome to AI Engineering with Modal, your hands-on guide to building and deploying production-grade AI systems with nothing but Python. This course is designed to transform your workflow. We'll ditch the complex YAML files, Dockerfiles, and cloud configuration panels.

Instead, you'll learn how to define your entire AI infrastructure-from custom container images and on-demand GPUs to persistent storage and scalable web endpoints-directly within your Python code. This is a project-based course where you won't just learn the theory; you'll build and deploy real-world AI applications from the ground up:A Scalable ASR Pipeline: Build a robust system to transcribe long audio files in parallel using a GPU-accelerated Automatic Speech Recognition model. A Fine-Tuned Classification Model: Fine-tune a modern transformer model (ModernBERT) on a custom dataset for a text classification task and deploy it as a live API.

A High-Throughput LLM Endpoint: Launch an OpenAI-compatible API for a powerful Large Language Model (like Qwen or Gemma) using vLLM for blazingly fast inference. Building a Coding Agent with Modal Sandboxes: Build your own code interpreter Agent with an LLM and an isolated secure cloud environment for executing arbitrary python code. A High-Throughput Image Processing Pipeline: Build an Image Similarity Search Endpoint ApplicationImage Generation Endpoint with black-forest-labs/FLUX.

1-Krea-dev and Qwen ImageSetting up complex GPU environments with libraries such as flash-attention and axolotlDeploy remote MCP servers with custom tools and use them in MCP hosts such as Claude DesktopBy the end of this course, you'll be able to confidently take any AI model from a local script to a scalable, cloud-native application ready for production. What you will master:Modal Fundamentals: Go from zero to hero with Modal's core concepts, running functions remotely and in parallel. Infrastructure as Code: Build custom container images, reserve powerful GPUs (A100s, H100s), manage CPU/memory, and use persistent Volumes-all in Python.