AWS Certified Machine Learning Engineer – Associate (MLA-C01)
Design, build, train, tune, deploy, and operationalize machine learning models and scalable MLOps pipelines using Amazon SageMaker and AWS artificial intelligence services.
Official Exam Specification & Quick Facts
Question Difficulty Breakdown
Recommended Study Guides & Exam Preparation Blueprints
Reinforce your knowledge with domain breakdowns, trap question analyses, and architectural cheat sheets:
Exam Guidelines & Simulation Rules
Frequently Asked Questions (FAQ)
The MLA-C01 exam features 65 multiple-choice and multiple-response questions over 130 minutes. Cost is $150 USD with a passing threshold of 720/1000 (72%).
Domains include: (1) Data Preparation for Machine Learning (~28%), (2) ML Model Development (~26%), (3) Deployment and Orchestration (~22%), and (4) ML Solution Monitoring and Maintenance (~24%).
SageMaker Pipelines is a purpose-built CI/CD service for machine learning that orchestrates data prep, model training, hyperparameter tuning, model evaluation, and deployment in automated workflows.
Real-Time endpoints provide dedicated instances with persistent sub-second response. Serverless endpoints scale down to zero when idle for intermittent traffic. Asynchronous endpoints handle large payloads (up to 1 GB) and long processing times (up to 1 hour).
SageMaker Model Monitor continuously compares incoming production inference requests against baseline training data distributions, alerting on data drift, concept drift, and model quality degradation.
SageMaker Feature Store is a centralized repository to store, share, and retrieve curated ML features. It provides low-latency online reads for inference and point-in-time offline reads for training.
SageMaker Clarify calculates pre-training and post-training fairness metrics across demographic attributes and uses SHAP values to explain individual and global feature importance.
Data Wrangler is an interactive visual tool in SageMaker Studio that simplifies data preparation and feature engineering with 300+ pre-configured data transformations without writing code.
SageMaker HPO automates model tuning using Bayesian search, Random search, or Hyperband early stopping algorithms to find optimal hyperparameter combinations.
The Model Registry catalogs models, manages model versions, tracks evaluation metrics, associates lineage, and governs production deployment approval workflows.
The MLA-C01 credential is valid for three years from the pass date.
MLA-C01 certifies MLOps Engineers, Machine Learning Developers, and AI Infrastructure Specialists earning average US salaries between $135,000 and $180,000.