Browse Exams — Mock Exams & Practice Tests

MLA-C01 Overview — Format, Domains & Who Should Take It

What to expect on AWS Certified Machine Learning Engineer — Associate (MLA-C01): exam format and timing, domain coverage and weights, question styles, recommended background, and an efficient study approach.

On this page

Exam at a glance

  • Exam name: AWS Certified Machine Learning Engineer — Associate (MLA-C01)
  • Level: Associate
  • Questions: 65 total (multiple-choice and multiple-response)
  • Time: 130 minutes
  • Delivery: Pearson VUE testing center or online proctored exam
  • Result: Scaled score (100–1000); minimum passing score: 720
  • Cost: 150 USD
  • Languages offered: English, Japanese, Korean, Simplified Chinese

Note: AWS includes scored and unscored questions; the exam guide indicates 50 scored + 15 unscored (total 65).

Domain breakdown (weights)

  • Domain 1: Data Preparation for Machine Learning (ML) — 28%
  • Domain 2: ML Model Development — 26%
  • Domain 3: Deployment and Orchestration of ML Workflows — 22%
  • Domain 4: ML Solution Monitoring, Maintenance, and Security — 24%

What the exam emphasizes (high level)

Expect scenario-driven items where you choose the best answer for:

  • Ingesting, transforming, validating, and preparing data for modeling
  • Selecting modeling approaches, training and tuning models, and analyzing performance
  • Choosing deployment endpoints and infrastructure, plus orchestration and CI/CD for ML workflows
  • Monitoring model inference and infrastructure, managing costs, and securing ML systems

The exam is very SageMaker-forward (Feature Store, Data Wrangler, Model Registry, monitoring and deployment patterns), with a strong MLOps and ops-reliability flavor.

Who should take MLA-C01

This exam is a strong fit for:

  • ML engineers and MLOps engineers working with Amazon SageMaker
  • Data engineers and backend engineers who deploy ML features into production systems
  • DevOps engineers supporting ML pipelines and model delivery

AWS’s intended candidate guidance: at least 1 year of experience using Amazon SageMaker and other AWS services for ML engineering, plus experience in a related role (for example, backend developer, DevOps engineer, data engineer, MLOps engineer, or data scientist).

Study plan (efficient)

  1. Pick a timeline: 30/60/90-day Study Plan →
  2. Work the Syllabus task-by-task; drill immediately after each task.
  3. Keep a miss log: convert misses into one-liner rules (“RAG isn’t the answer here—this is model monitoring”, “Choose serverless vs real-time endpoints based on latency and traffic shape”).
  4. Final 1–2 weeks: mixed sets + at least a couple timed runs; review every miss.
Study Plan