Exam Prep Standard Course: AWS Certified Machine Learning Engineer - Associate (MLA-C01 - English)

In this fundamental-level course from Amazon Web Services (AWS), you learn how to assess your preparedness for the AWS Certified Machine Learning Engineer - Associate (MLA-C01) exam. The exam validates a candidate’s ability to build, operationalize, and maintain machine learning (ML) solutions and pipelines by using the AWS Cloud.

Prepare for the exam by exploring the exam’s topic areas and how they align to developing on AWS and to specific areas of study. Gauge your understanding of topics and concepts from each task statement grouped by domain. Reinforce your knowledge and identify learning gaps with explanations of exam-style questions. Follow the instructor as they review exam-style questions. Learn test-taking strategies to identify incorrect responses.

The standard exam prep course is one step in the 4-step plan that you can use to prepare for your exam with confidence. To access resources for the comprehensive 4-step plan, enroll in the Enhanced Exam Prep Plan: AWS Certified Machine Learning Engineer - Associate (MLA-C01), which includes role-based training, hands-on labs, experiential learning, additional exam-style questions, a pretest, and flashcards. If you are already logged into AWS Skill Builder, use this link version to access the plan.

The Standard Exam Prep Plan: AWS Certified Machine Learning Engineer - Associate (MLA-C01) includes free resources for Steps 1–3 of the 4-step plan. If you are already logged into AWS Skill Builder, use this link version to access the plan.

AWS updates and occasionally retires services and features as part of ongoing development. While Exam Prep content is regularly updated, there are brief periods when our courses may not reflect the current state of AWS services. We recommend checking the latest AWS documentation and announcements for the most accurate and up-to-date information about the current availability of services and features.

In August 2024, AWS announced that we are removing access to a number of services or features for new customers, including several included in this course. These include: AWS CodeCommit, AWS DataPipeline, Amazon S3 Select, Amazon Glacier Select, and Amazon Forecast. We will remove references in the next course update.

Course level: Fundamental
Duration: 5.5 hours

Activities

This course includes the following:

• Videos by expert instructors who deliver presentations and review exam-style questions.
• Official Practice Questions written in the same style as AWS Certification exams. All questions include detailed feedback and recommended resources to help you prepare for the exam.

Course objectives

In this course, you will do the following:

1.    Understand the knowledge tested by the AWS Certified Machine Learning Engineer - Associate (MLA-C01) exam.

2.    Evaluate your gaps in knowledge of the exam topics.

Intended audience 

This course is intended for individuals who meet the following requirements:

1.    Have at least 1 year of experience using Amazon SageMaker and other AWS services for ML engineering.

2.    Have at least 1 year of experience in a related role such as a backend software developer, DevOps developer, data engineer, or data scientist.

3.    Are preparing for the AWS Certified Machine Learning Engineer - Associate (MLA-C01) exam.

Prerequisites

These are the prerequisites for the AWS Certified Machine Learning Engineer - Associate (MLA-C01) exam. 

General IT knowledge

Learners should have the following:

• Basic understanding of common ML algorithms and their use cases
• Data engineering fundamentals, including knowledge of common data formats, ingestion, and transformation to work with ML data pipelines
• Knowledge of querying and transforming data
• Knowledge of software engineering best practices for modular, reusable code development, deployment, and debugging
• Familiarity with provisioning and monitoring cloud and on-premises ML resources
• Experience with continuous integration and continuous delivery (CI/CD) pipelines and infrastructure as code (IaC)
• Experience with code repositories for version control and CI/CD pipelines

Recommended AWS knowledge

Learners should be able to do the following:

• Knowledge of SageMaker capabilities and algorithms for model building and deployment
• Knowledge of AWS data storage and processing services for preparing data for modeling
• Familiarity with deploying applications and infrastructure on AWS 
• Knowledge of monitoring tools for logging and troubleshooting ML systems
• Knowledge of AWS services for the automation and orchestration of CI/CD pipelines
• Understanding of AWS security best practices for identity and access management, encryption, and data protection

Recommended courses

Although we don't require that you take any specific training before you take an exam, we do recommend that have the underlying training and knowledge outlined in the previous two sections. If you need to refresh your knowledge, enroll in the Enhanced Exam Prep Plan: AWS Certified Machine Learning Engineer - Associate (MLA-C01). The learning plan includes all of following the recommended courses. If you are already logged into AWS Skill Builder, use this link version to access the plan. 

Digital courses

•  AWS ML Engineer Associate Curriculum Overview (45 minutes)
• Collect, Ingest, and Store Data (1 hour)
• Transform Data (1 hour)
• Validate Data and Prepare for Modeling (45 minutes)
• Choose a Modeling Approach (1 hour 30 minutes)
• Train Models (1 hour 30 minutes)
• Refine Models (2 hours)
• Analyze Model Performance (45 minutes)
• Select a Deployment Infrastructure (1 hour)
• Create and Script Infrastructure (1 hour 30 minutes)
• Automate Deployment (1 hour 15 minutes)
• Monitor Model Performance and Data Quality (2 hours 30 minutes)
• Monitor and Optimize Infrastructure and Costs (2 hours 30 minutes)
• Secure AWS ML Resources (2 hours 15 minutes)
• AWS ML Engineer Associate Curriculum Conclusion (10 minute)
• Planning a Machine Learning Project (30 minutes)
• Amazon Bedrock Getting Started (1 hour)
  
  

Experiential and game-based learning

• Train a Model with Amazon SageMaker (50 minutes)
• Orchestrate a Machine Learning Workflow using Amazon SageMaker Pipelines and SageMaker Model Registry (1 hour)
• Monitor a Model for Data Drift (1 hour)
• Machine Learning: Model Deployment Using Blue/Green Method (2 hours)
• Analyze and Prepare Data with Amazon SageMaker Data Wrangler and Amazon EMR (1 hour)
• AWS Cloud Quest: Machine Learning (time varies)
  
  

Some of this content might require an AWS Skill Builder subscription.

Course outline

Module 1: Get to know the exam with exam-style questions

• Introduction to AWS Certified Machine Learning Engineer - Associate (MLA-C01)
• Exam Guide: AWS Certified Machine Learning Engineer - Associate (MLA-C01)
• Introduction to Exam-Style Questions
• Overview and Instructions: Official Practice Question Set
• Official Practice Question Set: AWS Certified Machine Learning Engineer - Associate (MLA-C01)

Module 2: Refresh your AWS knowledge and skills

• AWS training suggestions
• Whitepapers and FAQs

Module 3: Review and practice

Machine Learning Introduction

• Machine Learning Overview
• Machine Learning Lifecycle

Domain 1:  Data Preparation for Machine Learning (ML)

• Introduction
• 1.1 Ingest and store data. 
• 1.2 Transform data and perform feature engineering.
• 1.3 Ensure data integrity and prepare data for modeling.
• Walkthrough questions
• Additional resources

Domain 2: ML Model Development

• Introduction
• 2.1 Choose a modeling approach. 
• 2.2 Train and refine models.
• 2.3 Analyze model performance.
• Walkthrough questions
• Additional resources

Domain 3: Deployment and Orchestration of ML Workflows 

• Introduction
• 3.1 Select deployment infrastructure based on existing architecture and requirements.
• 3.2 Create and script infrastructure based on existing architecture and requirements.
• 3.3 Use automated orchestration tools to set up continuous integration and continuous delivery (CI/CD) pipelines.
• Walkthrough questions
• Additional resources

Domain 4: ML Solution Monitoring, Maintenance, and Security

• Introduction
• 4.1 Monitor model interference.
• 4.2 Monitor and optimize infrastructure costs.
• 4.3 Secure AWS resources.
• Walkthrough questions
• Additional resources

Module 4: Register for the exam

Module 5: Course close

Module 6: Course survey