Free study guide · 2026 edition
AWS Certified Machine Learning Engineer — Associate
MLA-C01 is the practical, engineering-oriented ML certification AWS launched in 2024 — focused on building, deploying, and operating ML systems on SageMaker, Bedrock, and adjacent AWS services.
Last updated: May 15, 2026Author: FactualMinds AWS ArchitectsReviewed by: Palaniappan P · AWS Solutions Architect — Professional
Exam code
MLA-C01
Duration
130 minutes
Questions
65
Cost
$150 USD
Passing score
720 / 1000
Format
Multiple choice, multiple response, ordering, matching, and case study questions
Valid for
3 years
Recommended experience
1 year of ML engineering or data engineering experience, plus hands-on AWS exposure
Exam domains
4 domains · 23 topics
1 Data Preparation for Machine Learning
28%
Data Preparation for Machine Learning
- Data ingestion: S3, Glue, EMR Serverless, Kinesis Data Streams / Firehose, MSK
- Storage decisions for ML data: S3, S3 Tables (Iceberg), Aurora, DynamoDB
- Feature engineering: SageMaker Feature Store, AWS Glue DataBrew, pandas on SageMaker Studio
- Data quality: SageMaker Data Wrangler, Glue Data Quality, deequ
- Bias detection on training data: SageMaker Clarify, Macie for sensitive-data scanning
2 ML Model Development
26%
ML Model Development
- SageMaker built-in algorithms: XGBoost, Linear Learner, BlazingText, DeepAR
- Bring-your-own-container and bring-your-own-script training modes
- SageMaker JumpStart for pre-trained model deployment and fine-tuning
- Hyperparameter tuning with SageMaker AMT (automatic model tuning)
- Distributed training: data parallelism, model parallelism, SageMaker Smart Sifting
- Amazon Bedrock model customization: continued pre-training, fine-tuning Nova / Claude where supported
3 Deployment and Orchestration of ML Workflows
22%
Deployment and Orchestration of ML Workflows
- SageMaker endpoint types: real-time, serverless, asynchronous, batch transform, multi-model
- Inference optimization: SageMaker Inference Recommender, SageMaker Neo, instance selection
- SageMaker Pipelines for orchestration; EventBridge triggers; Step Functions for cross-service flows
- Model registry, model lineage, model approval workflows
- A/B testing and traffic shifting between model versions on SageMaker endpoints
- Bedrock provisioned throughput for predictable cost on high-volume inference
4 ML Solution Monitoring, Maintenance, and Security
24%
ML Solution Monitoring, Maintenance, and Security
- SageMaker Model Monitor: data drift, model quality, feature attribution drift, bias drift
- CloudWatch metrics and Application Signals for ML services
- Retraining triggers and automated retraining workflows
- Security: IAM roles for SageMaker, VPC endpoints, KMS encryption for training data and artifacts
- Cost optimization: Spot training, Savings Plans for SageMaker, multi-model endpoints
- Bedrock Guardrails for generative use cases, content-filter monitoring
Why MLA-C01 exists
AWS replaced the Machine Learning Specialty (MLS-C01) with the Machine Learning Engineer Associate (MLA-C01) to align with how ML actually ships in 2024–2026. The new exam emphasizes:
- MLOps over algorithms — Pipelines, monitoring, model registry, drift detection are heavier than algorithm internals.
- GenAI alongside predictive ML — Bedrock, fine-tuning, RAG patterns, prompt engineering are explicit objectives.
- Cost-aware deployment — Multi-model endpoints, serverless inference, Bedrock provisioned throughput show up in exam questions.
- Security and governance — Model risk, bias, drift, data classification at production scale.
Recommended 5-week study plan
Week 1 — Data preparation (10 hours) SageMaker Data Wrangler labs, Glue Data Quality, Feature Store walkthrough. Read the SageMaker Feature Store deep-dive.
Week 2 — Model development (10 hours) Train a built-in XGBoost model and a custom-script PyTorch model. Run SageMaker AMT. Try JumpStart fine-tuning on a small dataset.
Week 3 — Deployment patterns (10 hours) Deploy real-time, serverless, async, and multi-model endpoints. Try Inference Recommender. Set up SageMaker Pipelines with EventBridge triggers.
Week 4 — Monitoring + GenAI (10 hours) SageMaker Model Monitor walkthrough. Bedrock Knowledge Bases + Guardrails labs. Build a small RAG application end-to-end.
Week 5 — Practice exams + weak areas (8 hours) Two Tutorial Dojo practice sets. Review every wrong answer. Re-read the AWS Well-Architected Machine Learning Lens.
Related FactualMinds Content
Frequently asked questions
Should I take MLA-C01 or wait for the Generative AI Specialty?
Take MLA-C01 now. The Generative AI Specialty (currently in beta as of 2026) is positioned as a specialty layered on top of MLA-C01. MLA-C01 also covers GenAI workloads (Bedrock fine-tuning, RAG patterns, prompt engineering) and is broader — predictive ML plus generative — which most production teams need.
How is MLA-C01 different from the retiring MLS-C01?
MLS-C01 (Specialty) was deeper but narrower — heavy on classical ML algorithms and theoretical foundations. MLA-C01 (Associate) is broader and more practical, with explicit coverage of GenAI, SageMaker JumpStart, Bedrock, and MLOps patterns AWS recommends in 2025–2026. AWS is retiring MLS-C01 — MLA-C01 is the successor.
Can I take MLA-C01 without AIF-C01?
Yes. AIF-C01 is recommended but not required. If you have ML engineering experience, you can jump straight to MLA-C01.
Need this certification's expertise on your team?
FactualMinds engineers hold 50+ AWS certifications. Whether you're hiring, training, or staffing a project, we can match the right depth to your engagement.