Developing Machine Learning and Generative AI Solutions

Turn AI concepts into practical AWS solutions

Once you understand the foundations of artificial intelligence and machine learning, the next step is learning how to apply them to real problems.

On this course, you’ll explore how AWS services support the development of machine learning and generative AI solutions from initial use cases through to deployment and monitoring.

You’ll work with services such as Amazon SageMaker and Amazon Bedrock while examining the stages involved in preparing data, training and evaluating models, and selecting suitable approaches for different business needs.

Shape machine learning solutions from data to deployment

Explore the machine learning workflow from data preparation and model training through evaluation, deployment, and monitoring.

You’ll consider how model performance is assessed and how MLOps practices support more consistent and manageable machine learning lifecycles.

Work with generative AI and foundation models

Examine how foundation models power generative AI applications and explore techniques used to adapt them for specific tasks.

You’ll consider prompt engineering, fine-tuning, and other approaches for improving model relevance and performance.

Match AWS AI services to real-world needs

Compare different AWS tools and approaches and learn how to choose solutions based on the problem, available data, scalability, performance, and operational requirements.

By the end, you’ll have a clearer understanding of how machine learning and generative AI solutions move from idea to implementation using AWS services, preparing you to progress into security, compliance, governance, and responsible AI.

This course is for learners with foundational AI and machine learning knowledge who want to explore how AWS services support model development, generative AI, deployment, and monitoring. It is suitable for technical and business-facing AI practitioners.

This course is for learners with foundational AI and machine learning knowledge who want to explore how AWS services support model development, generative AI, deployment, and monitoring. It is suitable for technical and business-facing AI practitioners.

• Identify the core stages of the machine learning workflow, from data preparation through to deployment and monitoring.
• Discuss primary AWS services, such as Amazon SageMaker and Amazon Bedrock, used in machine learning and generative AI.
• Describe techniques used to adapt foundation models, including prompt engineering and fine-tuning.
• Explore standard MLOps practices for evaluating model performance and managing application lifecycles.
• Explain key criteria—such as data, performance, and scalability—used to select AWS tools for specific business needs.