MLA-C01 Preparation Details
Preparing for the MLA-C01 AWS Certified Machine Learning Engineer Associate certification exam? Start here with a complete, objective-wise MLA-C01 study guide designed to help you pass faster.
This guide brings together official AWS documentation, key concepts, and curated resources for every MLA-C01 exam objective, making it ideal for both beginners and last-minute revision.
Looking for the best MLA-C01 preparation resources in one place? This page covers everything you need to get exam-ready with confidence.
If this helped you, share it with others preparing for the MLA-C01 certification exam.
AWS Machine Learning Engineer Prep
| Coursera | AWS Machine Learning Engineer Associate Exam Prep |
| Udemy | AWS Certified Machine Learning Engineer Hands On! |
| Whizlabs | AWS Certified Machine Learning Engineer |
Content Domain 1: Data Preparation for Machine Learning (ML)
Task 1.1: Ingest and store data
Knowledge of: Data formats and ingestion mechanisms (for example, validated and non-validated formats, Apache Parquet, JSON, CSV, Apache ORC, Apache Avro, RecordIO)
AWS Glue supported data formats and compression formats
Amazon SageMaker Feature Store offline store data format
AWS Cloud Data Ingestion Patterns and Practices
Knowledge of: How to use the core AWS data sources (for example, Amazon S3, Amazon EFS, Amazon FSx for NetApp ONTAP)
What is Amazon Simple Storage Service?
What is Amazon Elastic File System?
What is Amazon FSx for NetApp ONTAP?
Knowledge of: How to use AWS streaming data sources to ingest data (for example, Amazon Kinesis, Apache Flink, Apache Kafka)
What is Amazon Kinesis Data Streams?
Welcome to the Amazon MSK Developer Guide
What is Amazon Managed Service for Apache Flink?
Data sources and ingestion – Amazon SageMaker AI Feature Store
Knowledge of: AWS storage options, including use cases and tradeoffs
Choosing an AWS storage service
Machine Learning Lens – AWS Well-Architected Framework
Data Analytics Lens – AWS Well-Architected Framework
Skills in: Extracting data from storage (for example, Amazon S3, Amazon EBS, Amazon EFS, Amazon RDS, Amazon DynamoDB) by using relevant AWS service options (for example, Amazon S3 Transfer Acceleration, Amazon EBS Provisioned IOPS)
What is Amazon Relational Database Service?
Amazon DynamoDB Developer Guide
Skills in: Choosing appropriate data formats (for example, Parquet, JSON, CSV, ORC) based on data access patterns
AWS Glue supported data formats and compression formats
Best practices design patterns: Optimizing Amazon S3 performance
Skills in: Ingesting data into Amazon SageMaker Data Wrangler and SageMaker Feature Store
Prepare ML data with Amazon SageMaker Data Wrangler
Create, store, and share features with Feature Store – Amazon SageMaker AI
Data sources and ingestion – Amazon SageMaker AI Feature Store
Skills in: Merging data from multiple sources (for example, by using programming techniques, AWS Glue, Apache Spark)
Apache Spark on Amazon EMR clusters
Connection types and options for ETL in AWS Glue
Skills in: Troubleshooting and debugging data ingestion and storage issues that involve capacity and scalability
Amazon Kinesis Data Streams quotas and limits
Skills in: Making initial storage decisions based on cost, performance, and data structure
Choosing an AWS storage service
Storage options for Amazon SageMaker AI – Machine Learning Lens
Task 1.2: Transform data and perform feature engineering
Knowledge of: Data cleaning and transformation techniques (for example, detecting and treating outliers, imputing missing data, combining, deduplication)
Prepare ML data with Amazon SageMaker Data Wrangler
Recommendations for choosing the right data preparation tool in SageMaker AI
Knowledge of: Feature engineering techniques (for example, data scaling and standardization, feature splitting, binning, log transformation, normalization)
Prepare ML data with Amazon SageMaker Data Wrangler
Create, store, and share features with Feature Store – Amazon SageMaker AI
Machine Learning Lens – AWS Well-Architected Framework
Knowledge of: Encoding techniques (for example, one-hot encoding, binary encoding, label encoding, tokenization)
Prepare ML data with Amazon SageMaker Data Wrangler
Built-in algorithms and pretrained models in Amazon SageMaker
Knowledge of: Tools to explore, visualize, or transform data and features (for example, SageMaker Data Wrangler, AWS Glue, AWS Glue DataBrew)
Prepare ML data with Amazon SageMaker Data Wrangler
Recommendations for choosing the right data preparation tool in SageMaker AI
Knowledge of: Services that transform streaming data (for example, AWS Lambda, Spark)
Using AWS Lambda with Amazon Kinesis – AWS Lambda
Apache Spark on Amazon EMR clusters
What is Amazon Managed Service for Apache Flink?
Knowledge of: Data annotation and labeling services that create high-quality labeled datasets
Use Amazon SageMaker Ground Truth to Label Data
Use Amazon SageMaker Ground Truth Plus to Label Data
Amazon Augmented AI (Amazon A2I) Developer Guide
Skills in: Transforming data by using AWS tools (for example, AWS Glue, DataBrew, Spark running on Amazon EMR, SageMaker Data Wrangler)
Prepare ML data with Amazon SageMaker Data Wrangler
Apache Spark on Amazon EMR clusters
Skills in: Creating and managing features by using AWS tools (for example, SageMaker Feature Store)
Create, store, and share features with Feature Store – Amazon SageMaker AI
Data sources and ingestion – Amazon SageMaker AI Feature Store
Amazon SageMaker Feature Store offline store data format
Skills in: Validating and labeling data by using AWS services (for example, SageMaker Ground Truth, Amazon Mechanical Turk)
Use Amazon SageMaker Ground Truth to Label Data
Use Amazon SageMaker Ground Truth Plus to Label Data
Amazon Augmented AI (Amazon A2I) Developer Guide
Task 1.3: Ensure data integrity and prepare data for modeling
Knowledge of: Pre-training bias metrics for numeric, text, and image data (for example, class imbalance [CI], difference in proportions of labels [DPL])
Detect Pre-training Data Bias – Amazon SageMaker AI
Pre-training Bias Metrics – Amazon SageMaker AI
What Is Fairness and Model Explainability for Machine Learning Predictions? – Amazon SageMaker
Knowledge of: Strategies to address CI in numeric, text, and image datasets (for example, synthetic data generation, resampling)
Amazon SageMaker Autopilot – Handle Imbalanced Data
Fairness, model explainability and bias detection with SageMaker Clarify
Use Amazon SageMaker Ground Truth to Label Data
Knowledge of: Techniques to encrypt data
AWS Key Management Service Developer Guide
Protect data at rest using encryption – Amazon SageMaker AI
Securing, protecting, and managing data – Storage Best Practices for Data and Analytics Applications
Knowledge of: Data classification, anonymization, and masking
Dynamic data masking in Amazon Redshift
AWS Privacy Reference Architecture – AWS Prescriptive Guidance
Knowledge of: Implications of compliance requirements (for example, PII, PHI, data residency)
Data residency – AWS Whitepaper
AWS Privacy Reference Architecture – AWS Prescriptive Guidance
Skills in: Validating data quality (for example, by using DataBrew and AWS Glue Data Quality)
Profiling data with AWS Glue DataBrew
Skills in: Identifying and mitigating sources of bias in data (for example, selection bias, measurement bias) by using AWS tools (for example, SageMaker Clarify)
Detect Pre-training Data Bias – Amazon SageMaker AI
Fairness, model explainability and bias detection with SageMaker Clarify
Pre-training Bias Metrics – Amazon SageMaker AI
Skills in: Preparing data to reduce prediction bias (for example, by using dataset splitting, shuffling, and augmentation)
Amazon SageMaker Autopilot – Handle Imbalanced Data
Use Amazon SageMaker Ground Truth to Label Data
Prepare – Machine Learning Lens – AWS Well-Architected Framework
Skills in: Configuring data to load into the model training resource (for example, Amazon EFS, Amazon FSx)
What is Amazon Elastic File System?
Amazon FSx for Lustre User Guide
Use File Systems in Amazon SageMaker Training Jobs
Storage options for Amazon SageMaker AI – Machine Learning Lens
Content Domain 2: ML Model Development
Task 2.1: Choose a modeling approach
Knowledge of: Capabilities and appropriate uses of ML algorithms to solve business problems
Types of Algorithms – Amazon SageMaker AI
Built-in algorithms and pretrained models in Amazon SageMaker
Machine Learning Lens – AWS Well-Architected Framework
Knowledge of: How to use AWS artificial intelligence (AI) services (for example, Amazon Translate, Amazon Transcribe, Amazon Rekognition, Amazon Bedrock) to solve specific business problems
Choosing an AWS machine learning service
Knowledge of: How to consider interpretability during model selection or algorithm selection
What Is Fairness and Model Explainability for Machine Learning Predictions? – Amazon SageMaker
Fairness, model explainability and bias detection with SageMaker Clarify
Knowledge of: Amazon SageMaker AI built-in algorithms and when to apply them
Built-in algorithms and pretrained models in Amazon SageMaker
Types of Algorithms – Amazon SageMaker AI
Use Amazon SageMaker Built-in Algorithms or Pre-trained Models
Skills in: Assessing available data and problem complexity to determine the feasibility of an ML solution
Choosing an AWS machine learning service
Prepare – Machine Learning Lens – AWS Well-Architected Framework
Recommendations for choosing the right data preparation tool in SageMaker AI
Skills in: Comparing and selecting appropriate ML models or algorithms to solve specific problems
Amazon Bedrock or Amazon SageMaker AI?
Choosing an AWS machine learning service
Types of Algorithms – Amazon SageMaker AI
Skills in: Choosing built-in algorithms, foundation models, and solution templates (for example, in SageMaker JumpStart and Amazon Bedrock)
Amazon SageMaker JumpStart pretrained models
Supported foundation models in Amazon Bedrock
Skills in: Selecting models or algorithms based on costs
Understanding intelligent prompt routing in Amazon Bedrock
Skills in: Selecting AI services to solve common business needs
Choosing an AWS machine learning service
Machine Learning (ML) and Artificial Intelligence (AI) – Overview of Amazon Web Services
Task 2.2: Train and refine models
Knowledge of: Elements in the training process (for example, epoch, steps, batch size)
Train a Model – Amazon SageMaker AI
Distributed training in Amazon SageMaker AI
Machine Learning Lens – AWS Well-Architected Framework
Knowledge of: Methods to reduce model training time (for example, early stopping, distributed training)
Stop Training Jobs Early – Amazon SageMaker AI
Distributed training in Amazon SageMaker AI
SageMaker distributed model parallel best practices
Knowledge of: Factors that influence model size
Model compression overview – Amazon SageMaker AI
Distributed training in Amazon SageMaker AI
Optimized generative AI inference recommendations – Amazon SageMaker AI
Knowledge of: Methods to improve model performance
Automatic model tuning with SageMaker AI
Understand the hyperparameter tuning strategies available in Amazon SageMaker AI
Machine Learning Lens – AWS Well-Architected Framework
Knowledge of: Benefits of regularization techniques (for example, dropout, weight decay, L1 and L2)
Prevent Overfitting in Machine Learning – Amazon SageMaker AI
Amazon SageMaker Model Monitor
AWS Cloud Adoption Framework for AI, ML, and Generative AI
Knowledge of: Hyperparameter tuning techniques (for example, random search, Bayesian optimization)
Understand the hyperparameter tuning strategies available in Amazon SageMaker AI
Automatic model tuning with SageMaker AI
How hyperparameter tuning works – Amazon SageMaker AI
Knowledge of: Model hyperparameters and their effects on model performance (for example, number of trees in a tree-based model, number of layers in a neural network)
Built-in algorithms and pretrained models in Amazon SageMaker
Understand the hyperparameter tuning strategies available in Amazon SageMaker AI
Train a Model – Amazon SageMaker AI
Knowledge of: Methods to integrate models that were built outside SageMaker AI into SageMaker AI
Use your own training code – Amazon SageMaker AI
Custom model import – Amazon Bedrock
Amazon SageMaker Model Registry
Skills in: Using SageMaker AI built-in algorithms and common ML libraries to develop ML models
Built-in algorithms and pretrained models in Amazon SageMaker
Train a Model – Amazon SageMaker AI
Skills in: Using SageMaker AI script mode with SageMaker AI supported frameworks to train models (for example, TensorFlow, PyTorch)
Train with script mode using the SageMaker Python SDK
Use TensorFlow with the SageMaker Python SDK
Use PyTorch with the SageMaker Python SDK
Skills in: Using custom datasets to fine-tune pre-trained models (for example, Amazon Bedrock, SageMaker JumpStart)
Customize an Amazon Bedrock model by fine-tuning
Amazon SageMaker JumpStart pretrained models
Fine-tune Amazon Bedrock models
Skills in: Performing hyperparameter tuning (for example, by using SageMaker AI automatic model tuning [AMT])
Automatic model tuning with SageMaker AI
Stop Training Jobs Early – Amazon SageMaker AI
Understand the hyperparameter tuning strategies available in Amazon SageMaker AI
Skills in: Integrating automated hyperparameter optimization capabilities
Automatic model tuning with SageMaker AI
Skills in: Preventing model overfitting, underfitting, and catastrophic forgetting (for example, by using regularization techniques, feature selection)
Detect Pre-training Data Bias – Amazon SageMaker AI
Amazon SageMaker Model Monitor
Stop Training Jobs Early – Amazon SageMaker AI
Skills in: Combining multiple training models to improve performance (for example, ensembling, stacking, boosting)
Built-in algorithms and pretrained models in Amazon SageMaker
Machine Learning Lens – AWS Well-Architected Framework
Skills in: Reducing model size (for example, by altering data types, pruning, updating feature selection, compression)
Model compression overview – Amazon SageMaker AI
Optimized generative AI inference recommendations – Amazon SageMaker AI
Skills in: Managing model versions for repeatability and audits (for example, by using the SageMaker Model Registry)
Amazon SageMaker Model Registry
Register a model version – Amazon SageMaker AI
Amazon SageMaker Experiments – Manage ML experiments
Task 2.3: Analyze model performance
Knowledge of: Model evaluation techniques and metrics (for example, confusion matrix, heat maps, F1 score, accuracy, precision, recall, RMSE, ROC, AUC)
MLPER-03: Define relevant evaluation metrics – Machine Learning Lens
Evaluate the model – Amazon SageMaker AI
Metrics and validation – Amazon SageMaker Autopilot
Choose the best performing model using Amazon Bedrock evaluations
Knowledge of: Methods to create performance baselines
Amazon SageMaker Model Monitor
Amazon SageMaker Experiments – Manage ML experiments
MLPER-03: Define relevant evaluation metrics – Machine Learning Lens
Knowledge of: Methods to identify model overfitting and underfitting
Detect Pre-training Data Bias – Amazon SageMaker AI
Stop Training Jobs Early – Amazon SageMaker AI
Amazon SageMaker Model Monitor
Knowledge of: Metrics available in SageMaker Clarify to gain insights into ML training data and models
Fairness, model explainability and bias detection with SageMaker Clarify
What Is Fairness and Model Explainability for Machine Learning Predictions? – Amazon SageMaker
Pre-training Bias Metrics – Amazon SageMaker AI
Knowledge of: Convergence issues
SageMaker Training Compiler Troubleshooting
Understand the hyperparameter tuning strategies available in Amazon SageMaker AI
Distributed training in Amazon SageMaker AI
Skills in: Selecting and interpreting evaluation metrics and detecting model bias
MLPER-03: Define relevant evaluation metrics – Machine Learning Lens
Fairness, model explainability and bias detection with SageMaker Clarify
Post-training Data and Model Bias Metrics – Amazon SageMaker AI
Skills in: Assessing tradeoffs between model performance, training time, and cost
MLPER-03: Define relevant evaluation metrics – Machine Learning Lens
Understand the hyperparameter tuning strategies available in Amazon SageMaker AI
Skills in: Performing reproducible experiments by using AWS services
Amazon SageMaker Experiments – Manage ML experiments
Amazon SageMaker Model Registry
Skills in: Comparing the performance of a shadow variant to the performance of a production variant
SageMaker shadow testing overview – Amazon SageMaker AI
Create a shadow test in Amazon SageMaker AI
Skills in: Using SageMaker Clarify to interpret model outputs
Fairness, model explainability and bias detection with SageMaker Clarify
What Is Fairness and Model Explainability for Machine Learning Predictions? – Amazon SageMaker
Feature Attributions that Use Shapley Values – Amazon SageMaker AI
Skills in: Using SageMaker Model Debugger to debug model convergence
Use SageMaker Debugger to debug model training
SageMaker Debugger built-in rules – Amazon SageMaker AI
Content Domain 3: Deployment and Orchestration of ML Workflows
Task 3.1: Select deployment infrastructure based on existing architecture and requirements
Knowledge of: Deployment best practices (for example, versioning, rollback strategies)
Deploy models for inference – Amazon SageMaker AI
Amazon SageMaker Model Registry
MLPER-12: Choose an optimal deployment option in the cloud – Machine Learning Lens
Knowledge of: AWS deployment services (for example, Amazon SageMaker AI)
Deploy models for inference – Amazon SageMaker AI
Model Hosting FAQs – Amazon SageMaker AI
Supported features – Amazon SageMaker AI inference options
Knowledge of: Methods to serve ML models in real time and in batches
Deploy models for real-time inference – Amazon SageMaker AI
Use Batch Transform to Get Inferences from Large Datasets – Amazon SageMaker AI
Deploy models with Amazon SageMaker Asynchronous Inference
Knowledge of: How to provision compute resources in production environments and test environments (for example, CPU, GPU)
Amazon SageMaker AI instance types
Optimized generative AI inference recommendations – Amazon SageMaker AI
Inference cost optimization best practices – Amazon SageMaker AI
Knowledge of: Model and endpoint requirements for deployment endpoints (for example, serverless endpoints, real-time endpoints, asynchronous endpoints, batch inference)
Supported features – Amazon SageMaker AI inference options
Deploy models with Amazon SageMaker Serverless Inference
Deploy models with Amazon SageMaker Asynchronous Inference
MLPER-12: Choose an optimal deployment option in the cloud – Machine Learning Lens
Knowledge of: How to choose appropriate containers (for example, provided or customized)
Use Your Own Inference Code with Hosting Services – Amazon SageMaker AI
Adapting your own Docker container to work with SageMaker AI
Amazon SageMaker AI pre-built Docker images
Knowledge of: Methods to optimize models on edge devices (for example, SageMaker Neo)
Optimize Machine Learning Models with SageMaker Neo
Getting Started with Edge Manager – Amazon SageMaker AI
Skills in: Evaluating performance, cost, and latency tradeoffs
Inference cost optimization best practices – Amazon SageMaker AI
MLPER-12: Choose an optimal deployment option in the cloud – Machine Learning Lens
Model Hosting FAQs – Amazon SageMaker AI
Skills in: Choosing the appropriate compute environment for training and inference based on requirements (for example, GPU or CPU specifications, processor family, networking bandwidth)
Optimized generative AI inference recommendations – Amazon SageMaker AI
Amazon SageMaker AI instance types
Inference cost optimization best practices – Amazon SageMaker AI
Skills in: Selecting the correct deployment orchestrator (for example, Apache Airflow, SageMaker Pipelines)
What Is Amazon Managed Workflows for Apache Airflow?
Skills in: Selecting multi-model or multi-container deployments
Multi-model endpoints – Amazon SageMaker AI
Multi-container endpoints – Amazon SageMaker AI
Skills in: Selecting the correct deployment target (for example, SageMaker AI endpoints, Kubernetes, Amazon ECS, Amazon EKS, AWS Lambda)
Deploy models for inference – Amazon SageMaker AI
What is Amazon Elastic Kubernetes Service?
What is Amazon Elastic Container Service?
Skills in: Choosing model deployment strategies (for example, real time, batch)
MLPER-12: Choose an optimal deployment option in the cloud – Machine Learning Lens
Supported features – Amazon SageMaker AI inference options
Inference cost optimization best practices – Amazon SageMaker AI
Task 3.2: Create and script infrastructure based on existing architecture and requirements
Knowledge of: Difference between on-demand and provisioned resources
Increase model invocation capacity with Provisioned Throughput in Amazon Bedrock
Deploy models with Amazon SageMaker Serverless Inference
Inference cost optimization best practices – Amazon SageMaker AI
Knowledge of: How to compare scaling policies
Auto scaling policy overview – Amazon SageMaker AI
Automatic scaling of Amazon SageMaker AI models
What is Application Auto Scaling?
Knowledge of: Tradeoffs and use cases of infrastructure as code (IaC) options (for example, AWS CloudFormation, AWS CDK)
Getting started with the AWS CDK
AWS CDK vs AWS CloudFormation – AWS Prescriptive Guidance
Knowledge of: Containerization concepts and AWS container services
What is Amazon Elastic Container Registry?
What is Amazon Elastic Container Service?
What is Amazon Elastic Kubernetes Service?
Adapting your own Docker container to work with SageMaker AI
Knowledge of: How to use SageMaker AI endpoint auto scaling policies to meet scalability requirements (for example, based on demand, time)
Automatic scaling of Amazon SageMaker AI models
Auto scaling policy overview – Amazon SageMaker AI
Autoscale an asynchronous endpoint – Amazon SageMaker AI
Skills in: Applying best practices to enable maintainable, scalable, and cost-effective ML solutions (for example, automatic scaling on SageMaker AI endpoints, dynamically adding Spot Instances, by using Amazon EC2 instances, by using Lambda behind the endpoints)
Automatic scaling of Amazon SageMaker AI models
Managed Spot Training in Amazon SageMaker AI
Inference cost optimization best practices – Amazon SageMaker AI
Skills in: Automating the provisioning of compute resources, including communication between stacks (for example, by using CloudFormation, AWS CDK)
Getting started with the AWS CDK
Nested stacks – AWS CloudFormation
Skills in: Building and maintaining containers (for example, Amazon ECR, Amazon EKS, Amazon ECS, by using BYOC with SageMaker AI)
What is Amazon Elastic Container Registry?
Adapting your own Docker container to work with SageMaker AI
What is Amazon Elastic Kubernetes Service?
Skills in: Configuring SageMaker AI endpoints within the VPC network
Give SageMaker AI access to resources in your Amazon VPC
Use SageMaker AI with VPC endpoints – Amazon SageMaker AI
Skills in: Deploying and hosting models by using the SageMaker AI SDK
Deploy models for inference – Amazon SageMaker AI
Skills in: Choosing specific metrics for auto scaling (for example, model latency, CPU utilization, invocations per instance)
Auto scaling policy overview – Amazon SageMaker AI
Automatic scaling of Amazon SageMaker AI models
Monitor Amazon SageMaker with Amazon CloudWatch
Task 3.3: Use automated orchestration tools to set up CI/CD pipelines
Knowledge of: Capabilities and quotas for AWS CodePipeline, AWS CodeBuild, and AWS CodeDeploy
Knowledge of: Automation and integration of data ingestion with orchestration services
What Is Amazon Managed Workflows for Apache Airflow?
Knowledge of: Version control systems and basic usage (for example, Git)
Source control integrations for AWS CodePipeline
Knowledge of: CI/CD principles and how they fit into ML workflows
AWS Cloud Adoption Framework for AI, ML, and Generative AI
Knowledge of: Deployment strategies and rollback actions (for example, blue/green, canary, linear)
CodeDeploy deployment configurations
Blue/green deployments on AWS – AWS Whitepaper
SageMaker shadow testing overview – Amazon SageMaker AI
Knowledge of: How code repositories and pipelines work together
Source control integrations for AWS CodePipeline
Skills in: Configuring and troubleshooting CodeBuild, CodeDeploy, and CodePipeline, including stages
Skills in: Applying continuous deployment flow structures to invoke pipelines (for example, Gitflow, GitHub Flow)
Source control integrations for AWS CodePipeline
Skills in: Using AWS services to automate orchestration (for example, to deploy ML models, automate model building)
AWS Step Functions Developer Guide
Skills in: Configuring training and inference jobs (for example, by using Amazon EventBridge rules, SageMaker Pipelines, CodePipeline)
Run Amazon SageMaker Pipelines jobs from EventBridge
Skills in: Creating automated tests in CI/CD pipelines (for example, integration tests, unit tests, end-to-end tests)
Testing and validations – Amazon SageMaker AI
SageMaker shadow testing overview – Amazon SageMaker AI
Skills in: Building and integrating mechanisms to retrain models
Amazon SageMaker Model Monitor
Content Domain 4: ML Solution Monitoring, Maintenance, and Security
Task 4.1: Monitor model inference
Knowledge of: Drift in ML models
MLPERF06-BP03 Evaluate data drift – Machine Learning Lens
MLPERF06-BP04 Monitor, detect, and handle model performance degradation – Machine Learning Lens
Bias drift for models in production – Amazon SageMaker AI
Feature attribution drift for models in production – Amazon SageMaker AI
Knowledge of: Techniques to monitor data quality and model performance
Data and model quality monitoring with Amazon SageMaker Model Monitor
Model Monitor FAQs – Amazon SageMaker AI
Fairness, model explainability and bias detection with SageMaker Clarify
Knowledge of: Design principles for ML lenses relevant to monitoring
MLPERF06-BP03 Evaluate data drift – Machine Learning Lens
MLPERF06-BP04 Monitor, detect, and handle model performance degradation – Machine Learning Lens
Skills in: Monitoring models in production (for example, by using Amazon SageMaker Model Monitor)
Amazon SageMaker Model Monitor
Data and model quality monitoring with Amazon SageMaker Model Monitor
Model Monitor FAQs – Amazon SageMaker AI
Skills in: Monitoring workflows to detect anomalies or errors in data processing or model inference
Amazon SageMaker Model Monitor
Using Amazon CloudWatch alarms
Skills in: Detecting changes in the distribution of data that can affect model performance (for example, by using SageMaker Clarify)
Bias drift for models in production – Amazon SageMaker AI
Feature attribution drift for models in production – Amazon SageMaker AI
Fairness, model explainability and bias detection with SageMaker Clarify
Skills in: Monitoring model performance in production by using A/B testing
SageMaker shadow testing overview – Amazon SageMaker AI
Safely validate models in production – Amazon SageMaker AI
MLPERF06-BP04 Monitor, detect, and handle model performance degradation – Machine Learning Lens
Task 4.2: Monitor and optimize infrastructure and costs
Knowledge of: Key performance metrics for ML infrastructure (for example, utilization, throughput, availability, scalability, fault tolerance)
Monitor Amazon SageMaker with Amazon CloudWatch
Amazon SageMaker AI runtime metrics
Performance Efficiency Pillar – AWS Well-Architected Framework
Knowledge of: Monitoring and observability tools to troubleshoot latency and performance issues (for example, AWS X-Ray, Amazon CloudWatch Lambda Insights, Amazon CloudWatch Logs Insights)
Using Lambda Insights in Amazon CloudWatch
Analyzing log data with CloudWatch Logs Insights
Knowledge of: How to use AWS CloudTrail to log, monitor, and invoke re-training activities
Log Amazon SageMaker API calls with AWS CloudTrail
Knowledge of: Differences between instance types and how they affect performance (for example, memory optimized, compute optimized, general purpose, inference optimized)
Amazon SageMaker AI instance types
Optimized generative AI inference recommendations – Amazon SageMaker AI
Inference cost optimization best practices – Amazon SageMaker AI
Knowledge of: Capabilities of cost analysis tools (for example, AWS Cost Explorer, AWS Billing and Cost Management, AWS Trusted Advisor)
What is AWS Billing and Cost Management?
Knowledge of: Cost tracking and allocation techniques (for example, resource tagging)
Tagging your Amazon SageMaker AI resources
Using AWS cost allocation tags
Skills in: Configuring and using tools to troubleshoot and analyze resources (for example, CloudWatch Logs, CloudWatch alarms)
What is Amazon CloudWatch Logs?
Using Amazon CloudWatch alarms
Monitor Amazon SageMaker with Amazon CloudWatch
Skills in: Creating CloudTrail trails
Creating a trail for an organization – AWS CloudTrail
Log Amazon SageMaker API calls with AWS CloudTrail
Skills in: Setting up dashboards to monitor performance metrics (for example, by using Amazon QuickSight, CloudWatch dashboards)
Using Amazon CloudWatch dashboards
Skills in: Monitoring infrastructure (for example, by using Amazon EventBridge events)
Run Amazon SageMaker Pipelines jobs from EventBridge
Monitor Amazon SageMaker with Amazon CloudWatch
Skills in: Rightsizing instance families and sizes (for example, by using SageMaker AI Inference Recommender and AWS Compute Optimizer)
SageMaker AI Inference Recommender
AWS Compute Optimizer User Guide
Skills in: Monitoring and resolving latency and scaling issues
Auto scaling policy overview – Amazon SageMaker AI
Automatic scaling of Amazon SageMaker AI models
Monitor Amazon SageMaker with Amazon CloudWatch
Skills in: Preparing infrastructure for cost monitoring (for example, by applying a tagging strategy)
Tagging your Amazon SageMaker AI resources
Using AWS cost allocation tags
AWS Tagging Best Practices – AWS Prescriptive Guidance
Skills in: Troubleshooting capacity concerns that involve cost and performance (for example, provisioned concurrency, service quotas, auto scaling)
Amazon SageMaker AI service quotas
Automatic scaling of Amazon SageMaker AI models
Automatically scale Provisioned Concurrency for a serverless endpoint – Amazon SageMaker AI
Skills in: Optimizing costs and setting cost quotas by using appropriate cost management tools (for example, AWS Cost Explorer, AWS Trusted Advisor, AWS Budgets)
Managing your costs with AWS Budgets
Skills in: Optimizing infrastructure costs by selecting purchasing options (for example, Spot Instances, On-Demand Instances, Reserved Instances, SageMaker AI Savings Plans)
Managed Spot Training in Amazon SageMaker AI
Inference cost optimization best practices – Amazon SageMaker AI
Task 4.3: Secure AWS resources
Knowledge of: IAM roles, policies, and groups that control access to AWS services (for example, IAM, bucket policies, SageMaker Role Manager)
Identity and access management for Amazon SageMaker AI
How to use SageMaker AI execution roles
AWS managed policies for Amazon SageMaker AI
Knowledge of: SageMaker AI security and compliance features
Security in Amazon SageMaker AI
Protect data at rest using encryption – Amazon SageMaker AI
Give SageMaker AI access to resources in your Amazon VPC
Knowledge of: Controls for network access to ML resources
Give SageMaker AI access to resources in your Amazon VPC
Use SageMaker AI with VPC endpoints
Knowledge of: Security best practices for CI/CD pipelines
Securing DevOps – AWS Cloud Adoption Framework
Skills in: Configuring least privilege access to ML artifacts
Security best practices in IAM
Identity and access management for Amazon SageMaker AI
IAM Access Analyzer policy generation
Skills in: Configuring IAM policies and roles for users and applications that interact with ML systems
How to use SageMaker AI execution roles
Creating IAM policies – AWS IAM
Skills in: Monitoring, auditing, and logging ML systems to ensure continued security and compliance
Log Amazon SageMaker API calls with AWS CloudTrail
Monitor Amazon SageMaker with Amazon CloudWatch
Skills in: Troubleshooting and debugging security issues
Troubleshoot IAM – AWS Identity and Access Management
Log Amazon SageMaker API calls with AWS CloudTrail
Skills in: Building VPCs, subnets, and security groups to securely isolate ML systems
Subnets for your VPC – Amazon VPC
Security groups for your VPC – Amazon VPC
Give SageMaker AI access to resources in your Amazon VPC
This brings us to the end of the MLA-C01 AWS Certified Data Engineer Associate exam study guide.
What do you think? Let me know in the comments section if I have missed out on anything. Also, I love to hear from you how your preparation is going on!
In case you are preparing for other AWS certification exams, check out the AWS study guides for those exams.
Follow Me to Receive Updates on MLA-C01 Exam
Want to be notified as soon as I post? Subscribe to the RSS feed / leave your email address in the subscribe section. Share the article to your social networks with the below links so it can benefit others.
