Machine Learning Engineering on AWS
Build, deploy, and operationalize LLMs, AI agents, and generative AI systems on AWS
Created by Joshua Arvin Lat
Explore how to design, build, and manage generative AI systems and AI agents using AWS. Gain hands-on experience with AWS services to automate and operationalize large language models and AI workflows. Develop the practical skills needed to create secure, production-ready AI solutions in the cloud.
Packt | May 2026 | 588 min
What You Will Learn
You will work through real-world scenarios that show how to create, deploy, and manage AI agents and generative AI applications on AWS. Each topic is explained with practical examples, guiding you step by step as you use AWS tools to automate, secure, and scale your machine learning projects. By the end, you will have built complete AI systems ready for production.
Key Features
- Build and deploy AI agents using Amazon Bedrock and Strands Agents
- Fine-tune and evaluate large language models with Amazon SageMaker
- Automate end-to-end LLMOps workflows using SageMaker Pipelines
Target Audience
Designed for AI engineers, data scientists, and technology leaders who already understand the basics of AI, machine learning, and cloud engineering. If you want to deepen your skills in building, deploying, and operationalizing generative AI and LLMs on AWS, this course will help you move from foundational knowledge to advanced, hands-on expertise.
