MLA-C01 AWS Machine Learning Engineer – Associate
- Vendor
- AWS
- Level
- Associate
- Questions
- 65
- Time
- 130 min
- Domains
- 4
- In the bank
- 395
Practice 395 questionsTake a timed mock examDay-by-day study plan
Exam update: MLA-C02 replaces this exam (beta since 2026-09-29, generally available on 2027-01-14). MLA-C01 ended in English on 2026-09-28 and retires in all languages on 2027-01-14. For the new version, open MLA-C02. MLA-C02 exam page.
The exam at a glance
| Level | Associate |
|---|---|
| Questions | 65 |
| Time | 130 minutes (about 2 minutes per question) |
| Passing mark | 720 on a scaled score of 100–1,000 |
| Last day to take it | Jan 14, 2027 |
Domains and weights
| Domain | Weight | Practice questions here |
|---|---|---|
| D1 · Data Preparation for ML | 28% | 105 |
| D2 · ML Model Development | 26% | 97 |
| D3 · Deployment and Orchestration | 22% | 83 |
| D4 · Monitoring, Maintenance, and Security | 24% | 110 |
33 of the 395 practice questions (8%) ask for more than one answer.
D1 · Data Preparation for ML 28%
Tasks in the official exam guide (3)
D2 · ML Model Development 26%
Model development questions give a modeling goal plus a constraint (no labels, thousands of related series, a training run that stalls, versions that need approval) and ask which SageMaker capability or algorithm fits. Most options are real SageMaker features, so the work is matching each requirement to the feature built for it and ruling out tools that belong to a later stage.
What to watch for
- Decide whether labeled data exists before looking at algorithms. Finding unusual points without labels calls for an unsupervised method; supervised options assume labeled examples.
- Place each tool in the lifecycle: some inspect a training job while it runs, others watch an endpoint after deployment. A problem seen during training needs a training-time tool.
- For forecasting across many related products, including new ones with little history, think of one model trained across all series that can also give ranges, not one model per item.
Tasks in the official exam guide (3)
D3 · Deployment and Orchestration 22%
Deployment scenarios combine a hosting pattern with a process rule: many rarely used models, a risk team that must sign off, a pipeline step that fails now and then, or auditors who want to trace a model back to its source. The right answer is usually a managed feature that enforces the rule, while distractors only notify after the fact or multiply idle infrastructure.
What to watch for
- Count the models and estimate their traffic. Many small, rarely called models that share a container suggest one shared endpoint rather than one endpoint each.
- In CloudFormation, SageMaker endpoint scaling comes from Application Auto Scaling resources (a scalable target and a scaling policy), not from the resource types used for EC2 fleets.
- Treat approval and traceability as controls inside the pipeline: a gate tied to Model Registry status, and identifiers such as commit and run IDs recorded on the model version.
Tasks in the official exam guide (3)
D4 · Monitoring, Maintenance, and Security 24%
Here the model is already in production and the stem reports a symptom: slow requests across services, accuracy that fades, idle endpoints, rising spend, or a permission that does not reach a job. First decide whether the need is to detect, prevent or explain a problem, then find the service that does exactly that. Tools that only analyze data later are common distractors.
What to watch for
- When accuracy drops while the inputs look the same, the link between inputs and outcomes has changed. That calls for monitoring against ground-truth labels, not only input distribution checks.
- For a slow request that passes through several services, ask which signal can split the total time by service. Metrics and log lines alone rarely locate the slow hop.
- Separate alerting on spend from analyzing it. A requirement to be warned when a budget is forecast or passed needs a service that sends alerts, not a reporting tool.
Tasks in the official exam guide (3)
A study order that works
The 28-day study plan for MLA-C01 takes the domains in this order. Each day has a short reading, key terms and a quiz from the bank.
- Days 1–8: D1 · Data Preparation for ML
- Days 9–15: D2 · ML Model Development
- Days 16–21: D3 · Deployment and Orchestration
- Days 22–27: D4 · Monitoring, Maintenance, and Security
- Day 28: Final Day: Full Practice Exam and Exam-Day Checklist
Recent changes to these questions
- : 10 answer choice sets changed, 5 answer keys corrected, 10 explanations rewritten
- : 8 explanations rewritten
- : 7 answer choice sets changed, 7 answer keys corrected, 7 explanations rewritten
- : 21 explanations rewritten
- : 5 explanations rewritten
About these questions
Every question is original, written from the public exam guide and checked against the vendor's own documentation. None comes from a real exam. Each one has an explanation of why the answer is right and why the other options are wrong. How the questions are written.