AWS Certified Machine Learning Engineer – Associate Practise Exam

Who it is for

• Candidates preparing for the AWS Certified Machine Learning Engineer – Associate Certification (MLA-C01).
• Practitioners who use Amazon SageMaker and other AWS services for ML engineering and need practice building, deploying, monitoring, and securing ML pipelines.

What this exam covers

• Data Preparation for Machine Learning (ML) — 28%
• ML Model Development — 26%
• Deployment and Orchestration of ML Workflows — 22%
• ML Solution Monitoring, Maintenance, and Security — 24%

What you will practice

• Ingest and transform ML data with Amazon S3, Amazon SageMaker Data Wrangler, Amazon SageMaker Feature Store, AWS Glue, and Amazon EMR, and check quality and bias with AWS Glue DataBrew and Amazon SageMaker Clarify.
• Choose Amazon SageMaker algorithms and AWS AI services including Amazon Bedrock, train and tune models, and evaluate them with Amazon SageMaker Clarify and Amazon SageMaker Model Debugger.
• Deploy Amazon SageMaker endpoints and containers on Amazon ECS or Amazon EKS, and orchestrate ML CI/CD with Amazon SageMaker Pipelines and AWS CodePipeline.
• Monitor production models with Amazon SageMaker Model Monitor and Amazon CloudWatch, optimize cost with AWS Cost Explorer, and secure ML systems with IAM and Amazon VPC.

About this practice exam

The AWS Certified Machine Learning Engineer – Associate exam tests a candidate’s ability to build, operationalize, deploy, and maintain machine learning (ML) solutions and pipelines by using the AWS Cloud: ingest, transform, validate, and prepare data for ML modeling; select general modeling approaches, train models, tune hyperparameters, analyze model performance, and manage model versions; choose deployment infrastructure and endpoints, provision compute resources, and configure auto scaling; set up continuous integration and continuous delivery (CI/CD) pipelines to automate orchestration of ML workflows; monitor models, data, and infrastructure to detect issues; and secure ML systems through access controls, compliance features, and best practices. This practice exam prepares you for AWS Certified Machine Learning Engineer – Associate (MLA-C01) across Data Preparation for Machine Learning (ML), ML Model Development, Deployment and Orchestration of ML Workflows, and ML Solution Monitoring, Maintenance, and Security.

The exam emphasizes ingesting and transforming data with Amazon S3, Amazon SageMaker Data Wrangler, Amazon SageMaker Feature Store, AWS Glue, AWS Glue DataBrew, and Amazon EMR; choosing Amazon SageMaker built-in algorithms and AWS AI services including Amazon Bedrock, Amazon Rekognition, Amazon Transcribe, and Amazon Translate; training, hyperparameter tuning, and evaluation with Amazon SageMaker JumpStart, Amazon SageMaker Clarify, and Amazon SageMaker Model Debugger; deploying real-time, asynchronous, serverless, and batch inference with Amazon SageMaker endpoints, Amazon ECS, Amazon Elastic Kubernetes Service (Amazon EKS), and AWS Lambda; orchestrating ML CI/CD with Amazon SageMaker Pipelines, AWS CodePipeline, AWS CodeBuild, AWS CodeDeploy, and Amazon EventBridge; monitoring with Amazon SageMaker Model Monitor and Amazon CloudWatch; and securing ML systems with AWS Identity and Access Management (IAM) and Amazon VPC. It does not primarily assess designing and architecting full end-to-end ML solutions, setting up best practices and guiding ML strategies, handling integration with a wide array of services or new tools and technologies, working deeply in two or more ML domains such as natural language processing (NLP) or computer vision, or quantizing models and analyzing the impact on accuracy.

The official AWS Certified Machine Learning Engineer – Associate (MLA-C01) exam is 65 questions in 130 minutes. This practice exam follows the four official Machine Learning Engineer – Associate domains and their published weights.

The certification validates understanding of:

• Data Preparation for Machine Learning (ML): ingestion from Amazon S3, Amazon EFS, Amazon FSx, Amazon RDS, Amazon DynamoDB, and Amazon Kinesis; formats including Apache Parquet, JSON, CSV, and Apache ORC; Amazon SageMaker Data Wrangler and Amazon SageMaker Feature Store; transformation with AWS Glue, AWS Glue DataBrew, Spark on Amazon EMR, and AWS Lambda; labeling with Amazon SageMaker Ground Truth and Amazon Mechanical Turk; data quality with AWS Glue Data Quality; bias checks with Amazon SageMaker Clarify; and compliance implications including personally identifiable information (PII) and protected health information (PHI).
• ML Model Development: AWS AI services including Amazon Translate, Amazon Transcribe, Amazon Rekognition, and Amazon Bedrock; Amazon SageMaker built-in algorithms and Amazon SageMaker JumpStart; training with TensorFlow and PyTorch in Amazon SageMaker script mode; Amazon SageMaker automatic model tuning (AMT); Amazon SageMaker Model Registry; evaluation metrics including F1 score, RMSE, and Area Under the ROC Curve (AUC); Amazon SageMaker Clarify; and Amazon SageMaker Model Debugger.
• Deployment and Orchestration of ML Workflows: Amazon SageMaker real-time, serverless, asynchronous, and batch inference endpoints; Amazon SageMaker Neo; Amazon ECS, Amazon EKS, and AWS Lambda; infrastructure as code with AWS CloudFormation and AWS Cloud Development Kit (AWS CDK); containers with Amazon Elastic Container Registry (Amazon ECR); auto scaling; CI/CD with AWS CodePipeline, AWS CodeBuild, AWS CodeDeploy, Amazon SageMaker Pipelines, and Amazon EventBridge; and deployment strategies including blue/green, canary, and linear.
• ML Solution Monitoring, Maintenance, and Security: Amazon SageMaker Model Monitor, Amazon SageMaker Clarify, and A/B testing; Amazon CloudWatch, AWS X-Ray, AWS CloudTrail, and Amazon EventBridge; cost tools including AWS Cost Explorer, AWS Trusted Advisor, and AWS Budgets; Amazon SageMaker Inference Recommender and AWS Compute Optimizer; IAM and Amazon SageMaker Role Manager; and Amazon VPC isolation of ML systems.