AWSRetiringAWS Certified Machine Learning Engineer - Associate
The AWS Certified Machine Learning Engineer - Associate certification validates your ability to build, operationalize, deploy, and maintain machine learning solutions and pipelines on AWS. It is designed for ML engineers and MLOps practitioners with at least one year of hands-on experience using Amazon SageMaker and other AWS ML services. Earning this credential positions you for in-demand machine learning roles and demonstrates that you can turn ML models into reliable, production-grade workloads.
368 practice questions · Updated 2026-07-30
4Domains
12Objectives
135Concepts
368Questions
MLA-C01 Curriculum
Every domain, objective, and concept the MLA-C01 exam measures.
- Data formats and ingestion mechanisms
- Core AWS data sources
- AWS streaming data sources
- AWS storage options and tradeoffs
- Extracting data from storage
- Choosing appropriate data formats
- Ingesting into SageMaker Data Wrangler and Feature Store
- Merging data from multiple sources
- Troubleshooting ingestion and storage issues
- Initial storage decisions
- Data Cleaning Techniques
- Feature Engineering Techniques
- Encoding Techniques
- Data Exploration and Transformation Tools
- Streaming Data Transformation Services
- Data Annotation and Labeling Services
- AWS Tools for Data Transformation
- Feature Store Management
- Data Validation and Labeling Workflows
- Pre-training bias metrics
- Strategies to address class imbalance
- Data encryption techniques
- Data classification, anonymization, and masking
- Compliance requirements for data handling
- Validating data quality with AWS tools
- Identifying and mitigating data bias with SageMaker Clarify
- Preparing data to reduce prediction bias
- Configuring data for model training resources
- Algorithm capabilities and business use cases
- AWS AI services for business problems
- Interpretability in model selection
- SageMaker built-in algorithms
- Data and problem feasibility assessment
- Model and algorithm comparison and selection
- SageMaker JumpStart and Bedrock options
- Cost-based model and algorithm selection
- AI service selection for common needs
- Training process elements
- Reducing training time
- Factors influencing model size
- Improving model performance
- Regularization techniques
- Hyperparameter tuning techniques
- Model hyperparameters and effects
- Integrating external models into SageMaker
- SageMaker built-in algorithms and libraries
- SageMaker script mode
- Fine-tuning pre-trained models
- SageMaker automatic model tuning
- Preventing overfitting and underfitting
- Ensembling and model combination
- Reducing model size
- Model version management
- Confusion Matrix
- Classification Metrics
- Regression Metrics
- ROC and AUC
- Performance Baselines
- Overfitting and Underfitting
- SageMaker Clarify Metrics
- Convergence Issues
- Evaluation Metric Selection
- Model Bias Detection
- Performance Tradeoffs
- Reproducible Experiments
- Shadow Variant Comparison
- SageMaker Clarify Model Interpretation
- SageMaker Model Debugger
- Deployment best practices
- AWS deployment services
- Real-time and batch inference methods
- Compute provisioning for production and test
- Endpoint types and requirements
- Container selection
- Edge optimization with SageMaker Neo
- Performance, cost, and latency tradeoffs
- Compute environment selection for training and inference
- Deployment orchestrators
- Multi-model and multi-container deployments
- Deployment targets
- Model deployment strategies
- On-demand vs provisioned resources
- Scaling policy comparison
- Infrastructure as code options
- Containerization fundamentals
- SageMaker endpoint auto scaling
- Best practices for ML solutions
- Automating compute provisioning
- Building and maintaining containers
- SageMaker endpoints in VPC
- Deploying models with SageMaker SDK
- Auto scaling metrics selection
- AWS CodePipeline capabilities and quotas
- AWS CodeBuild capabilities and quotas
- AWS CodeDeploy capabilities and quotas
- Data ingestion automation with orchestration services
- Version control systems and Git basics
- CI/CD principles in ML workflows
- Deployment strategies and rollback actions
- Code repositories and pipeline integration
- Configuring CodeBuild stages
- Troubleshooting CodeBuild issues
- Configuring CodeDeploy stages
- Troubleshooting CodeDeploy issues
- Configuring CodePipeline stages
- Troubleshooting CodePipeline issues
- Gitflow and GitHub Flow for ML pipelines
- Automating ML model deployment with AWS services
- Configuring training jobs with EventBridge rules
- Configuring inference jobs with EventBridge rules
- Using SageMaker Pipelines for orchestration
- Integrating CodePipeline with SageMaker
- Creating unit tests in CI/CD pipelines
- Creating integration tests in CI/CD pipelines
- Monitoring model inference
- Inference metrics
- Data drift detection
- Concept drift detection
- Monitoring tools and services
- Alerts and thresholds
- Remediation actions
- Infrastructure monitoring metrics
- Cost monitoring tools
- Optimizing compute resources
- Optimizing storage costs
- Monitoring model performance in production
- Infrastructure optimization for ML workloads
- Cost optimization for training and inference
- Alerting and automated responses
- AWS Identity and Access Management (IAM) for ML resources
- Encryption of data at rest and in transit
- Secure access to ML endpoints
- Network security for ML workloads
- Logging and monitoring for security
- Compliance and data governance
Ready to practice?Test your knowledge with exam-style questions or take an intelligent quiz tailored to your level.
Percentages reflect share of the current practice bank, not official exam weightings — no structured per-skill weight is published for MLA-C01, so none is invented.