How many questions are on the AWS Certified Machine Learning Engineer – Associate exam?

The AWS Certified Machine Learning Engineer – Associate exam has 65 questions, and the vendor's published description is: 65 questions; multiple choice and multiple response, 130 minutes.

How long do you have to complete the AWS Certified Machine Learning Engineer – Associate exam?

You get 130 minutes, which is about 120 seconds per question. The published format is: 65 questions; multiple choice and multiple response, 130 minutes.

What score do you need to pass the AWS Certified Machine Learning Engineer – Associate exam?

The passing score is 72% (720 or greater (on a scale of 100 to 1,000)).

What are the domains on the AWS Certified Machine Learning Engineer – Associate exam?

There are 5 domains: Model Development, ML Operations (MLOps), ML Security and Compliance, Deployment and Orchestration, Data Preparation for Machine Learning. The official weights are Model Development 26%, ML Operations (MLOps) 16%, ML Security and Compliance 12%, Deployment and Orchestration 28%, Data Preparation for Machine Learning 18%.

How should I use the domain weights when revising?

Weight by percentage, not by domain. 26% is the one where lost points cost you the most, and Certilum scores you per domain so you can see exactly where that is.

Does Certilum have practice questions for the AWS Certified Machine Learning Engineer – Associate exam?

Yes: 65 questions in our bank for this certification, each tagged to the exam domain it belongs to, with the official domain weights applied.

Exam format

AWS Certified Machine Learning Engineer – Associate Exam Format

MLA-C01

Everything the official exam blueprint specifies: question count, time limit, scoring and the weight each domain carries. The AWS Certified Machine Learning Engineer – Associate (MLA-C01) certification validates your ability to design, implement, deploy, and maintain machine learning solutions using AWS services. This exam focuses on practical, hands‑on skills in data preparation, model training, deployment, and MLOps. It targets individuals with at least one year of experience in ML engineering or a related role, emphasizing real‑world problem‑solving on the AWS cloud platform. Successful candidates demonstrate proficiency in using Amazon SageMaker, understanding ML workflows, and applying AWS best practices for security and operational excellence.

65 questions

130 min

72% to pass

5 domains

certilum

Exam facts at a glance

The published specifications for this certification.

Specification	Value
Questions	65
Time limit	130 minutes (120s per question)
Passing score	72% — 720 or greater (on a scale of 100 to 1,000)
Domains	5
Level	Associate
Question bank here	65 questions
Published format	65 questions; multiple choice and multiple response, 130 minutes
Source	Official exam specification, published by the vendor

Official domain weights

The percentage of the exam each domain carries. Weight your revision by these numbers, not by what you find hardest.

Domain	Weight	Topics	Practice Qs
Model Development	26%	Select appropriate algorithm or model architecture based on business requirements Train and fine‑tune models using Amazon SageMaker (e.g., automatic model tuning, hyperparameter optimization) Evaluate model performance using appropriate metrics (e.g., accuracy, precision, recall, AUC‑ROC) +2 more	17
ML Operations (MLOps)	16%	Automate model retraining pipelines (e.g., SageMaker Pipelines, Step Functions) Manage model registry and approve models for production (e.g., SageMaker Model Registry) Implement logging and auditing of ML workflows (e.g., CloudTrail, CloudWatch Logs) +1 more	10
ML Security and Compliance	12%	Implement data encryption at rest and in transit (e.g., KMS, S3 SSE) Apply least‑privilege IAM policies for ML resources Use private network connectivity (e.g., VPC endpoints, SageMaker in VPC) +1 more	8
Deployment and Orchestration	28%	Deploy models to endpoints for real‑time inference (e.g., SageMaker real‑time endpoints, Serverless Inference) Set up batch inference workflows (e.g., SageMaker batch transform, AWS Lambda triggers) Automate model deployment using CI/CD pipelines (e.g., SageMaker Pipelines, AWS CodePipeline) +1 more	18
Data Preparation for Machine Learning	18%	Ingest data from AWS data stores and streams (e.g., S3, Kinesis, Redshift) Identify and remediate data quality issues (e.g., missing values, duplicates, outliers) Transform and normalize data for ML model training (e.g., using SageMaker Processing jobs, feature engineering) +1 more	12

The heaviest domain is Model Development at 26%, and that is where lost points cost you the most. Certilum scores you per domain so you can see the difference between a knowledge gap and a formatting problem.

Note from the vendor record: Retiring: MLA-C02 beta registration opened September 1, 2026 (English only, $75 USD, 85 questions, 170 minutes), the last day to take MLA-C01 in English was September 28, 2026, MLA-C01 remains available in Japanese, Korean and Simplified Chinese until MLA-C02 GA, announced as January 14, 2027 when MLA-C01 retires in all languages. Certification is valid 3 years and remains active through its full validity period regardless of when earned; no prerequisites (recommended 1 year of ML engineering experience). The exam-guide HTML link on the certification page returned 404/403, so score, question and duration details were verified from AWS's official MLA-C01 exam-guide PDF (Version 1.0 MLA-C01). Official exam page