AIF-C01 Fundamentals of AI and ML Practice Question
A data scientist wants to deploy a custom model built with TensorFlow to Amazon SageMaker for real-time inference. Which TWO steps are required? (Choose two.)
⚠ Common exam trap
Many candidates think they must build a custom container (Option A) or convert the model (Option E), but SageMaker's pre-built TensorFlow containers eliminate those steps, and the key requirements are simply uploading artifacts to S3 and creating the endpoint configuration.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Upload the model artifacts to an S3 bucket
Option B is correct because SageMaker requires model artifacts (the trained TensorFlow SavedModel or model.tar.gz) to be stored in an Amazon S3 bucket, which is then referenced by the SageMaker model when deploying. Option D is correct because deploying to a real-time endpoint requires creating an endpoint configuration that specifies the production variant, instance type, and initial instance count, which is then used to create the endpoint. Option A is not required because the TensorFlow inference container is already provided and maintained by SageMaker as a prebuilt Docker image, so no custom ECR repository is needed unless using a custom container. Option C is not required because the model is already built with TensorFlow; a SageMaker training job is only needed if training within SageMaker. Option E is not required because SageMaker's TensorFlow container supports native TensorFlow SavedModel format, so ONNX conversion is unnecessary.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Create an Amazon ECR repository for the inference container
Why it's wrong here
An ECR repository is where the inference container image is stored, but the stem already supplies a trained TensorFlow model, so no container build is required. It is tempting because custom containers do need ECR, and that would be correct when bringing your own inference code rather than a prebuilt framework image.
- ✓
Upload the model artifacts to an S3 bucket
Why this is correct
SageMaker real-time endpoints pull model artefacts from Amazon S3, so the trained TensorFlow files must reside in a bucket the execution role can read. This satisfies the stem's deployment requirement: without artefacts in S3, CreateModel cannot locate the model data, and endpoint creation fails.
- ✗
Submit a training job to SageMaker
Why it's wrong here
Submitting a training job produces a model artefact, yet the TensorFlow model is already built, so training is redundant before real-time deployment. It is tempting because training jobs are a standard SageMaker step, and that would be correct when the model must be fitted on data inside SageMaker rather than exported from elsewhere.
- ✓
Create a SageMaker endpoint configuration
Why this is correct
An endpoint configuration defines the model to deploy and the instance type and count to provision. SageMaker needs it before creating the real-time endpoint, satisfying the deployment step that maps the model to serving capacity.
- ✗
Convert the model to ONNX format
Why it's wrong here
ONNX conversion is unnecessary because SageMaker's TensorFlow inference container serves native SavedModel artefacts directly. It is tempting because ONNX enables framework-agnostic portability, and that would be correct when deploying to a runtime lacking native TensorFlow support, such as certain edge or cross-framework serving stacks.
Quick reference
AWS S3 Storage Class Comparison
| Storage Class | Min Duration | Retrieval | Use Case |
|---|---|---|---|
| S3 Standard | None | Immediate | Frequently accessed data |
| S3 Standard-IA | 30 days | Immediate | Infrequent access, rapid retrieval |
| S3 One Zone-IA | 30 days | Immediate | Non-critical infrequent data |
| S3 Intelligent-Tiering | None | Immediate–hours | Unknown or changing access patterns |
| S3 Glacier Instant | 90 days | Milliseconds | Archive with instant retrieval |
| S3 Glacier Flexible | 90 days | Minutes–hours | Archive, flexible retrieval |
| S3 Glacier Deep Archive | 180 days | Hours | Long-term compliance archive |
Go deeper
Related to this question
About these practice questions
Courseiva writes every AIF-C01 question from scratch — 862 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AIF-C01 exam.