Chapter MLA-C01 associate tier

Machine Learning Engineer

Editor's note — A study companion for the Machine Learning Engineer exam — every domain rebuilt from scratch, with worked practice questions and an exam-grade timed simulation.

65 questions 130 minutes threshold 720/1000 4 domains official guide

begin — Practice Twenty questions, untimed, with full explanations after every answer. begin — Mock Examination 65 questions in 130:00, timed, scored.

4 domains · 20 topics

I. Data Preparation For Ml 28% weight

ML Data Ingestion and Storage Patterns AWS Glue ETL for ML Pipelines SageMaker Data Wrangler and Feature Engineering SageMaker Feature Store — Online vs Offline ML Data Quality, Integrity, and Labeling

II. Ml Model Development 26% weight

Modeling Approach Selection — JumpStart, Bedrock, and Custom SageMaker Training Jobs and Built-in Algorithms Automatic Model Tuning — Bayesian and Hyperparameter Optimization Distributed Training on SageMaker Model Evaluation — SageMaker Debugger, Clarify, and Experiments

III. Deployment And Orchestration Of Ml Workflows 22% weight

SageMaker Endpoint Types — Real-Time, Async, Serverless, and Batch ML Deployment Strategies — A/B Testing, Shadow, and Blue/Green SageMaker Pipelines and ML Workflow Orchestration ML CI/CD with CodePipeline and Automated Retraining SageMaker Model Registry and Versioning

IV. Ml Solution Monitoring Maintenance And Security 24% weight

SageMaker Model Monitor — Data Quality and Model Quality Model Monitor — Bias Drift and Feature Attribution Drift SageMaker CloudWatch Monitoring and Cost Optimization IAM, KMS, and VPC for SageMaker Workloads SageMaker Role Manager and Least-Privilege Patterns