# AWS ML Engineer Associate MLA-C02 practice exams

> Prepare for MLA-C02 with 315 practice questions across 5 full timed exams, weighted toward Data Preparation for ML and AI. Every answer is explained.

Page: https://devopscodelab.com/exams/aws-mla-c02/

315 questions in 5 timed practice tests. Each test has about 65 questions and a 130-minute limit. The pass mark is 72%. Results are split across the 4 exam domains.

## Exam at a glance

| Setting | Value |
| --- | --- |
| Practice tests | 5 |
| Questions in total | 315 |
| Questions per test | About 65 |
| Time limit per test | 130 minutes |
| Pass mark | 72% |
| Question types | Single answer and multiple answer (26 multiple-answer questions) |
| Level | Associate |
| Category | AI & Machine Learning |

These are the settings of our practice tests. Check the official AWS exam page for the current format before you book.

## Domains and weights

| Domain | Weight | Questions in our bank |
| --- | --- | --- |
| Data Preparation for ML and AI | 28% | 88 |
| ML Model and Foundation Model (FM) Development | 24% | 75 |
| Deployment and Orchestration of ML and AI Workflows | 24% | 76 |
| Operating, Monitoring, and Securing ML and AI Solutions | 24% | 76 |

## Price and access

- MLA-C02 practice exams: $12.99 for 12 months of access.
- Free mini exam: 15 questions with explanations (free account): https://devopscodelab.com/app/exams/aws-mla-c02/mini/
- All-Access subscription includes every exam: https://devopscodelab.com/pricing/
- 10 free questions with answers: https://devopscodelab.com/exams/aws-mla-c02/free-practice-questions/

## Sample questions

### Question 1 of 3

A team is assembling 20,000 prompt-response pairs from several internal sources to fine-tune a model. Some pairs have empty responses, some are exact duplicates, and some contain toxic language copied from forum posts. Which approach BEST validates training data integrity before the fine-tuning job?

- A. Fine-tune on all pairs, then attach a Bedrock guardrail to the custom model's inference requests in production
- B. Preprocess the data to drop empty and duplicate pairs and screen each pair with the Bedrock ApplyGuardrail API
- C. Fine-tune on the raw pairs and rely on the fine-tuning job's validation loss to downweight broken examples
- D. Deduplicate the pairs with an AWS Glue job and then increase the epoch count so that clean examples dominate

**Answer:** B

**Explanation:** Data integrity checks belong before training: removing empty and duplicate pairs and screening content with ApplyGuardrail, which evaluates text without invoking a model, keeps the model from learning toxic or broken behavior. Validation loss is reported by the job but does not filter or downweight training examples. Deduplicating alone still leaves empty and toxic pairs, and extra epochs make the model memorize them more strongly. An inference-time guardrail filters outputs but leaves the toxic behavior learned in the model.

### Question 2 of 3

A team oversampled the minority class by duplicating rows and then randomly split the data into training and validation sets. Validation recall is excellent, but recall in production is poor. What is the MOST likely cause?

- A. Duplicated minority rows landed in both splits and inflated validation recall
- B. Production data has drifted away from the training distribution since the model was deployed
- C. Duplicating rows shifted the predicted probabilities, so the threshold needs recalibration
- D. The validation split was too small, so its recall estimate had high variance

**Answer:** A

**Explanation:** Resampling before splitting puts copies of the same minority records in both sets, so the model is evaluated on examples it memorized; resampling must be applied only to the training split. A small validation set adds variance but does not systematically inflate recall. Probability shift from oversampling affects calibration in both validation and production alike, so it does not explain the gap. Drift is possible but is not the most likely cause when the validation result was produced by leaked duplicates.

### Question 3 of 3

A model uses a 'country' feature with about 190 distinct values and a 'product_size' feature with the ordered values small, medium, and large. The model is a neural network. Which encoding approach is MOST appropriate?

- A. Use one-hot encoding for product_size and ordinal encoding for country to keep the input layer small
- B. Use ordinal encoding for both features so that each feature becomes a single compact integer column
- C. Use an embedding or one-hot encoding for country, and ordinal encoding for product_size
- D. Use target encoding for both features, replacing each category with its mean label value

**Answer:** C

**Explanation:** Country is nominal, so it should not be given an artificial order; one-hot or a learned embedding represents it correctly. Product size has a natural order, so ordinal encoding preserves that information compactly. Ordinal encoding country implies a meaningless ranking between countries, even if it keeps the input small. Target encoding both features discards product_size's natural order in favor of label means and risks target leakage without careful cross-fitting.


## Study plans

### Two weeks

1. Day 1: take practice test 1 in exam mode to get a baseline.
2. Days 2 to 5: domain mode on Data Preparation for ML and AI and ML Model and Foundation Model (FM) Development, the two most heavily weighted domains.
3. Day 6: practice test 2 in exam mode, then the mistakes quiz.
4. Days 7 to 12: practice tests 3 to 5, one every other day, each followed by its mistakes quiz.
5. Days 13 and 14: final mode. Book the exam when your readiness stays above the pass mark.

### Four weeks

1. Week 1: one practice test in practice mode, reading every explanation. Note your two lowest domains.
2. Week 2: domain mode on those two domains, then a second practice test in exam mode.
3. Week 3: practice tests 3 and 4 in exam mode, with the mistakes and flagged quizzes after each.
4. Week 4: practice test 5 and final mode until your readiness holds above the pass mark.

## Questions about the MLA-C02 practice exams

**Are these real MLA-C02 exam questions?**

No. We write every question ourselves and map it to the published MLA-C02 exam objectives. We do not use leaked or recalled questions.

**Do the time limit and pass mark match the official exam?**

They match the settings of our practice tests. Exam providers change their format from time to time, so check the official exam page before you book.

**Can I try it before I pay?**

Yes. The free mini exam has 15 questions with full explanations and needs no account.

**How long do I keep access?**

A single-exam purchase gives you 12 months of access. All-Access includes this exam for as long as your subscription runs.

**What happens after I finish a test?**

You get a score, a pass or fail against the pass mark, a score per domain and every answer with its explanation.

Last updated November 2026.

DevOpsCode Lab is not affiliated with AWS. MLA-C02 and related names are trademarks of their owners. We write every question ourselves; these are not real exam questions.
