How to Deploy an ML Model Serverlessly on AWS?
Short answer
D Deploy the model by using an Amazon SageMaker endpoint.
Question
Key Takeaways
This question tests the ability to identify a fully managed, serverless ML inference solution; the trap is choosing EC2 or EKS, which require manual infrastructure management.
Amazon SageMaker endpoints provide a fully managed, serverless way to deploy machine learning models for real-time inference without provisioning or managing underlying infrastructure. Community consensus is 100% aligned on this answer.
Common mistake: Candidates often choose A (Amazon EC2) because it is a common deployment target, but EC2 requires provisioning, patching, and managing servers, violating the 'no infrastructure management' requirement.
Expert Analysis
Why Option D is Correct
Amazon SageMaker is a fully managed machine learning service that allows you to build, train, and deploy ML models at scale. When you deploy a model to a SageMaker endpoint, AWS automatically handles all the underlying infrastructure — including provisioning instances, load balancing, auto-scaling, and health monitoring. This perfectly satisfies the requirement of making predictions without managing servers or infrastructure. As community member aws_Tamilan noted, SageMaker automatically handles the provisioning, making it the ideal serverless ML deployment option.
Why the Other Options Are Wrong
- Option A (Amazon EC2): EC2 provides raw virtual servers. You are responsible for OS patching, runtime installation, scaling, and monitoring — directly contradicting the requirement.
- Option B (Amazon EKS): While EKS manages the Kubernetes control plane, you still manage worker nodes, container orchestration, and scaling policies. It is not a fully managed, serverless ML inference solution.
- Option C (Amazon CloudFront + S3): CloudFront is a CDN and S3 is object storage. Neither can execute ML model inference logic. This combination is used for static content delivery, not real-time predictions.
Community Consensus
The community voted 100% for Option D, with members like Jessiii and may2021_r confirming that SageMaker endpoints are the canonical serverless ML deployment pattern on AWS.
Official Reference
- https://docs.aws.amazon.com/sagemaker/latest/dg/how-it-works-deployment.html
- https://docs.aws.amazon.com/sagemaker/latest/dg/realtime-endpoints.html
These links open the official vendor documentation in a new tab.
Exam Strategy
When a question emphasizes 'no managing servers or infrastructure,' immediately look for fully managed or serverless AWS services (SageMaker endpoints, Lambda, Fargate). Eliminate options that require you to manage compute, OS, or orchestration layers.
Community Votes
100% of anonymous learners picked answer D. Votes are pick records left by other test-takers — they are not the verified answer.
Discussion 3 contributions
Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.
From public community threads 3
-
aws_Tamilan 👍 1 Answered DD. Deploy the model by using an Amazon SageMaker endpoint. Explanation: Amazon SageMaker is a fully managed service that enables you to quickly build, train, and deploy machine learning models at scale. Deploying a model using an Amazon SageMaker endpoint allows the company to make predictions without needing to manage servers or infrastructure. SageMaker automatically handles the provisioning of resources, scaling, and maintenance, making it an ideal solution for production-grade ML deployments.
-
may2021_r 👍 1 Answered DThe correct answer is D. Deploying the model using an Amazon SageMaker endpoint allows for serverless predictions.
-
Jessiii 👍 1 Answered DFully managed service for deploying ML models, allowing predictions without managing infrastructure.
Reader comments & corrections
No reader corrections yet — spotted an error or have a note? Share it below.
Related Analysis
Practice All AIF-C01 Questions
Access 100 questions with complete answers and detailed explanations.
View Full AIF-C01 Practice Test →