Amazon Exam MLA-C01 Topic 1 Question 5 Discussion

Actual exam question for Amazon's MLA-C01 exam

Question #: 5
Topic #: 1

An ML engineer needs to implement a solution to host a trained ML model. The rate of requests to the model will be inconsistent throughout the day.

The ML engineer needs a scalable solution that minimizes costs when the model is not in use. The solution also must maintain the model's capacity to respond to requests during times of peak usage.

Which solution will meet these requirements?

ACreate AWS Lambda functions that have fixed concurrency to host the model. Configure the Lambda functions to automatically scale based on the number of requests to the model.

BDeploy the model on an Amazon Elastic Container Service (Amazon ECS) cluster that uses AWS Fargate. Set a static number of tasks to handle requests during times of peak usage.

CDeploy the model to an Amazon SageMaker endpoint. Deploy multiple copies of the model to the endpoint. Create an Application Load Balancer to route traffic between the different copies of the model at the endpoint.

DDeploy the model to an Amazon SageMaker endpoint. Create SageMaker endpoint auto scaling policies that are based on Amazon CloudWatch metrics to adjust the number of instances dynamically.

Show Suggested Answer

Suggested Answer: D

by Josphine at Jun 11, 2025, 09:48 PM

Limited Time Offer

25%

Off

Get Premium MLA-C01 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Quentin

3 days ago

Option A is the clear choice here. Lambda functions can scale up and down automatically, and you don't have to worry about managing any infrastructure. Plus, it's probably the cheapest solution, which is key when the model's not in use.

upvoted 0 times

...

Omega

9 days ago

I see both points, but I personally think option D is more cost-effective in the long run.

upvoted 0 times

...

Samuel

16 days ago

I disagree, I believe option D is better as it can adjust the number of instances dynamically based on metrics.

upvoted 0 times

...

Michel

27 days ago

As a self-proclaimed 'ML Guru', I can tell you that option B is the way to go. ECS Fargate is like the Ferrari of container orchestration, and it'll handle those peak loads like a champ.

upvoted 0 times

Derick

15 days ago

I agree, ECS Fargate is definitely a solid choice for handling peak loads efficiently.

upvoted 0 times

...

Melissa

30 days ago

I'd go with C. Deploying multiple copies of the model to the SageMaker endpoint and using an ALB to load balance seems like a great way to handle the inconsistent traffic.

upvoted 0 times

...

Cordelia

1 months ago

I think option A is the best choice because it can automatically scale based on the number of requests.

upvoted 0 times

...

30 days ago

Option D seems the most suitable. The ability to dynamically scale the SageMaker endpoint based on CloudWatch metrics is exactly what the problem statement is looking for.

upvoted 0 times

...