AWS Certified Machine Learning Engineer - Associate MLA-C01

• Introduction
• AWS Console UI Update
• Setting Up an AWS Billing Alarm

• Intro: Data Ingestion and Storage
• Types of Data
• Properties of Data (The Three V's)
• Data Warehouses, Lakes, and Lakehouses
• Data Mesh
• ETL & ETL Pipelines and Orchestration
• Common Data Sources and Data Formats
• Amazon S3
• Amazon S3 Security Bucket Policy
• Amazon S3 – Versioning
• Amazon S3 – Replication
• Amazon S3 Replication – Notes
• Amazon S3 Storage Classes
• Amazon S3 Lifecycle Rules
• Amazon S3 Event Notifications
• Amazon S3 – Performance
• Amazon S3 – Encryption
• About DSSEKMS
• Amazon S3 Encryption Hands On
• Amazon S3 Default Encryption
• Amazon S3 Access Points
• Amazon S3 Object Lambda
• Amazon EBS
• Amazon EBS Elastic Volumes
• Amazon EFS
• Amazon EFS vs. Amazon EBS
• Amazon FSx
• Amazon Kinesis Data Streams
• Amazon Data Firehose
• Kinesis Tuning and Troubleshooting
• Amazon Managed Service for Apache Flink
• Kinesis Analytics Costs; RANDOM_CUT_FOREST
• Amazon MSK
• Amazon MSK – Connect
• Amazon MSK – Serverless
• Amazon Kinesis vs. Amazon MSK

• Intro: Data Transformation, Integrity, and Feature Engineering
• Elastic MapReduce (EMR) and Hadoop Overview
• EMR Serverless
• Apache Spark on EMR
• Feature Engineering and the Curse of Dimensionality
• Lab: Preparing Data for TFIDF with Spark and EMR Studio, Part 1
• Lab: Preparing Data for TFIDF with Spark and EMR Studio, Part 2
• Imputing Missing Data
• Dealing with Unbalanced Data
• Handling Outliers
• Binning, Transforming, Encoding, Scaling, and Shuffling
• UPDATE: SageMaker is now "SageMaker AI"
• SageMaker AI Overview
• SageMaker AI Domains
• Data Processing, Training, and Deployment with SageMaker AI
• Amazon SageMaker Ground Truth and Label Generation
• Amazon Mechanical Turk
• SageMaker Data Wrangler
• Demo: SageMaker Studio, Canvas, and Data Wrangler
• SageMaker Model Monitor and SageMaker Clarify
• Partial Dependence Plots (PDPs), Shapley values, and SHAP
• SageMaker Feature Store
• SageMaker Canvas
• AWS Glue
• AWS Glue Studio
• AWS Glue Data Quality
• AWS Glue DataBrew
• Demo: Glue DataBrew
• Handling PII in DataBrew Transformations
• Intro to Amazon Athena
• Athena and Glue
• Athena and CREATE TABLE AS SELECT
• Athena Performance
• Athena ACID Transactions
• Athena FineGrained Access
• AWS Managed AI Services
• Intro: AWS Managed AI Services
• Why AWS Managed Services?
• Amazon Comprehend
• Amazon Comprehend Custom Models
• Amazon Comprehend Hands On
• Amazon Translate
• Amazon Transcribe
• Amazon Polly
• Amazon Rekognition
• Amazon Lex
• Amazon Personalize
• Amazon Textract
• Amazon Kendra
• Amazon Augmented AI
• Amazon's Hardware for AI
• Amazon Lookout
• Amazon Fraud Detector
• Amazon Q Business
• Amazon Q Apps
• Amazon Q Developer
• Sagemaker BuiltIn Algorithms
• Intro: SageMaker BuiltIn Algorithms
• Introducing Amazon SageMaker
• SageMaker Input Modes
• Linear Learner in SageMaker
• XGBoost in SageMaker
• LightGBM in SageMaker
• Seq2Seq in SageMaker
• DeepAR in SageMaker
• BlazingText in SageMaker
• Object2Vec in SageMaker
• Object Detection in SageMaker
• Image Classification in SageMaker
• Semantic Segmentation in SageMaker
• Random Cut Forest in SageMaker
• Neural Topic Model in SageMaker
• Latent Dirichlet Allocation (LDA) in SageMaker
• KNearestNeighbors (KNN) in SageMaker
• KMeans Clustering in SageMaker
• Principal Component Analysis (PCA) in SageMaker
• Factorization Machines in SageMaker
• IP Insights in SageMaker
• Model Training, Tuning and Evaluation
• Intro: Model Training, Tuning, and Evaluation
• Introduction to Deep Learning
• Activation Functions
• Convolutional Neural Networks
• Recurrent Neural Networks
• Tuning Neural Networks
• Regularization Techniques for Neural Networks (Dropout, Early Stopping)
• L1 and L2 Regularization
• The Vanishing Gradient Problem
• The Confusion Matrix
• Precision, Recall, F1, AUC, and more
• RMSE, Rsquared, MAE
• Ensemble Methods: Bagging and Boosting
• Automatic Model Tuning (AMT) in SageMaker
• Hyperparameter Tuning in AMT
• SageMaker Autopilot / AutoML
• SageMaker Studio, SageMaker Experiments
• SageMaker Debugger
• SageMaker Model Registry
• Analyzing Training Jobs with Tensor Board
• SageMaker Training at Large Scale: Training Compiler, Warm Pools
• SageMaker Checkpointing, Cluster Health Checks, Automatic Restarts
• SageMaker Distributed Training Libraries and Distributed Data Parallelism
• SageMaker Model Parallelism Library
• Elastic Fabric Adapter (EFA) and MiCS

• Intro: Generative AI Model Fundamentals
• The Transformer Architecture
• SelfAttention and AttentionBased Neural Networks
• Applications of Transformers
• Generative PreTrained Transformers: How they Work, Part 1
• Generative PreTrained Transformers: How they Work, Part 2
• LLM Key Terms and Controls (tokens, embeddings, temperature, etc.)
• FineTuning and Transfer Learning with Transformers
• Lab: Tokenization and Positional Encoding with SageMaker Notebooks
• Lab: MultiHeaded, Masked SelfAttention in SageMaker
• Lab: Using GPT within a SageMaker Notebook
• AWS Foundation Models and SageMaker JumpStart with Generative AI
• Lab: Using Amazon SageMaker JumpStart with Hugging face

• Intro: Building Generative AI Applications with Bedrock
• Building Generative AI with Amazon Bedrock and Foundation Models
• A note on Bedrock model access
• Lab: Chat, Text, and Image Foundation Models in the Bedrock Playground
• FineTuning Custom Models and Continuous PreTraining with Bedrock
• RetrievalAugmented Generation (RAG) Fundamentals with Bedrock
• Vector Stores and Embeddings with Amazon Bedrock Knowledge Bases
• Implementing RAG with Amazon Bedrock Knowledge Bases
• Lab: Building and Querying a RAG System with Amazon Bedrock Knowledge Bases
• Addendum: New chunking strategies in Bedrock
• Content Filtering with Amazon Bedrock Guardrails
• Lab: Building and Testing Guardrails with Amazon Bedrock
• Building LLM Agents / Agentic AI with Amazon Bedrock Agents
• Lab: Build a Bedrock Agent with Action Groups, Knowledge Bases, and Guardrails
• WARNING: Make sure you deleted all of your OpenSearch resources!
• Other Amazon Bedrock Features (Model Evaluation, Bedrock Studio, Watermarks)

• Intro: MLOps
• Deployment Guardrails and Shadow Tests
• SageMaker's Inner Details and Production Variants
• SageMaker On the Edge: SageMaker Neo and IoT Greengrass
• SageMaker Resource Management: Instance Types and Spot Training
• SageMaker Resource Management: Automatic Scaling
• SageMaker: Deploying Models for Inference
• SageMaker Serverless Inference and Inference Recommender
• SageMaker Inference Pipelines
• SageMaker Model Monitor
• Model Monitor Data Capture
• MLOps with SageMaker, Kubernetes, SageMaker Projects, and SageMaker Pipelines
• What is Docker?
• Amazon ECS
• Amazon ECS Create Cluster Hands On
• Amazon ECS Create Service Hands On
• Amazon ECR
• Amazon EKS
• AWS Batch
• AWS CloudFormation
• AWS CDK
• AWS CodeDeploy
• AWS CodeBuild
• AWS CodePipeline
• Git Review: Architecture and Commands
• Gitflow, GitHub Flow
• Amazon EventBridge
• AWS Step Functions
• AWS Step Functions: State Machines and States
• Amazon Managed Workflows for Apache Airflow (MWAA)
• AWS Lake Formation
• Lake Formation Data Filters

• Intro: Security, Identity, and Compliance
• Principle of Least Privilege
• Data Masking and Anonymization
• SageMaker Security: Encryption at Rest and in Transit
• SageMaker Security: VPC's, IAM, Logging and Monitoring
• IAM Introduction: Users, Groups, Policies
• IAM Users & Groups Hands On
• AWS Console Simultaneous Signin
• IAM Policies
• IAM MFA
• IAM Roles
• Encryption 101
• AWS KMS
• Amazon Macie
• AWS Secrets Manager
• AWS WAF
• AWS Shield
• VPC, Subnets, Internet Gateway, NAT Gateway
• NACL, Security Groups, VPC Flow Logs
• VPC Peering, Endpoints, VPN, Direct Connect
• VPC Cheat Sheet & Closing Comments
• AWS PrivateLink

• Intro: Management and Governance
• Amazon CloudWatch Metrics
• Amazon CloudWatch Logs
• Amazon CloudWatch Logs Unified Agent
• Amazon CloudWatch Alarms
• Amazon CloudWatch Alarms Hands On
• AWS XRay
• Overview of Amazon Quicksight
• Types of Visualizations, and When to Use Them
• Amazon CloudTrail
• AWS Config
• CloudWatch vs. CloudTrail vs. Config
• AWS Budgets
• AWS Cost Explorer
• AWS Trusted Advisor

• Intro: Machine Learning Best Practices
• Designing ML Systems with AWS: Responsible AI
• ML Design Principles and Lifecycle
• ML Business Goal Identification
• Framing the ML Problem
• Data Processing
• Model Development
• Deployment
• Monitoring
• AWS WellArchitected Machine Learning Lens

1+ years of ML engineering experience, familiarity with Python and at least one ML framework (scikit-learn, PyTorch, or TensorFlow), and working knowledge of core AWS services (S3, IAM, Lambda, EC2) are recommended.

The MLA-C01 focuses on MLOps and operational aspects of ML on AWS, while the MLS-C01 Specialty covers ML theory and algorithm selection. They complement each other and the MLA-C01 adds practical deployment depth.

A significant module covers Amazon Bedrock — foundation models, RAG patterns, prompt engineering, guardrails, agents, and fine-tuning — reflecting its growing weight in the MLA-C01 exam.

Yes. Running training jobs on SageMaker with custom Docker containers pushed to ECR, deploying ML models on EKS, and using Kubernetes operators for ML orchestration are all covered.

SageMaker Model Monitor (data quality, model quality, bias, feature attribution drift), CloudWatch custom metrics, Clarify explainability reports, and Grafana dashboards for operational visibility.

65 questions (multiple choice and multiple response) in 130 minutes, passing score 720 out of 1000. Focus areas: data preparation, model training, deployment and inference, and ML solution monitoring/optimisation.