MLOps & Model Deployment

This course teaches you how to build end-to-end machine learning applications. It covers topics such as feature engineering, intermediate machine learning models, and recommender systems.

Taught by instructors from Live Kit and an Andreessen Horowitz portfolio company, this course covers how to build scalable voice agents using a cloud infrastructure. It delves into the components of a voice pipeline and real-time networking protocols.

An instructor-led, live training that teaches participants how to apply AI tools, computer vision, and machine learning techniques to automate inspections and improve product quality in manufacturing.

This course provides a comprehensive exploration of AI-powered data engineering, equipping participants with the skills to design, orchestrate, and deploy intelligent data pipelines tailored for ML and DL applications. The training also covers advanced tools and platforms used in building AI-driven pipelines, including TensorFlow Extended (TFX), MLflow, Apache Airflow, and Kubeflow.

This complete Generative AI course takes you from beginner to advanced with hands-on projects, real-world applications, and career-ready skills. You’ll learn the foundations of Generative AI, explore Large Language Models (LL Ms), master frameworks like LangChain, Llama Index, CrewAI, and PydanticAI, and deploy your own AI solutions on the cloud. The course is tailored to equip you with both the knowledge and practical experience required to step into a Generative AI Engineer role.Each section includes quizzes & coding exercises to help you test your knowledge and reinforce your skills.What you’ll learn in each section1. Introduction – Get started with the course, understand what you will learn & set up Python environments (Colab, Jupyter, Py Charm).2. Generative AI – Foundation – Understand AI vs ML vs DL vs GenAI, dive into Large Language Models, and learn the Transformer architecture.3. Accessing LL Ms in Python – Use OpenAI, Gemini, Groq, and Ollama LL Ms, and connect them through LangChain and Llama Index.4. Prompt Engineering – Explore prompt templates, zero-shot, and few-shot prompting to effectively interact with LL Ms.5. Building GenAI Chatbots – Build and deploy chatbots step by step using LangChain, Llama Index, Streamlit UI, and Streamlit Cloud.6. Retrieval-Augmented Generation (RAG) – Understand RAG, build RAG pipelines with LangChain and Llama Index, and create a PDF Q&A bot.7. AI Agents – Learn what AI agents are and build agents with PydanticAI, Auto Gen, and CrewAI for multi-agent workflows.8. LLM Deployment – Deploy open-source LL Ms with Ollama, Docker, and vLLM, and set them up on AWS EC2 for real-world usage.