SageMaker Endpoint High Availability: Multi-AZ Deployments and Auto Scaling
A company is deploying a machine learning model to a SageMaker endpoint and wants to ensure that the endpoint is resilient to instance failures. Which THREE steps should the company take to achieve high availability? (Choose THREE.)
Quick Answer
High availability for a SageMaker endpoint comes from combining redundancy at the infrastructure level with automatic recovery at the instance level, and this scenario's correct actions work together across those two layers. Deploying the endpoint into a VPC with subnets spanning at least two Availability Zones is the infrastructure-level piece: SageMaker distributes the endpoint's instances across those subnets, so if an entire Availability Zone experiences an outage, instances in the other zone continue serving traffic, giving the endpoint fault isolation that a single-AZ deployment simply cannot provide. Enabling auto-scaling adds the recovery-level piece on top of that redundancy: rather than just adding capacity for traffic spikes, auto-scaling also works to maintain the desired instance count by replacing instances that become unhealthy, so a failure at the individual-instance level gets self-healed without manual intervention. The two mechanisms address different failure modes, one protects against a zone-level outage, the other protects against instance-level failures within a zone, which is why both are needed rather than either alone. This is a pattern worth recognizing broadly across AWS: true high availability usually requires both spreading resources across independent failure domains, like Availability Zones, and having an automated mechanism to detect and replace unhealthy components. When a question asks for multiple steps to make an endpoint or service resilient to failures, expect the correct combination to include both multi-AZ placement and an automated health-and-recovery mechanism.
⚠ Common exam trap
It's easy for candidates to think a single large instance or a single Availability Zone is sufficient for high availability, but AWS's shared responsibility model requires you to architect for failure across multiple AZs and use auto-scaling to replace unhealthy instances automatically.
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
✓
Deploy the endpoint in a VPC with subnets in at least two Availability Zones.
Deploying the endpoint in a VPC with subnets in at least two Availability Zones ensures that if one Availability Zone fails, the endpoint can still serve traffic from the other zone. SageMaker endpoints distribute instances across the specified subnets, so multi-AZ deployment provides fault isolation and high availability at the infrastructure level.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Deploy the endpoint in a VPC with subnets in at least two Availability Zones.
Why this is correct
Provides AZ redundancy.
- ✗
Use a single instance type with the largest size to handle capacity.
Why it's wrong here
Single instance is a single point of failure.
- ✓
Configure the endpoint with an initial instance count of at least 2.
Why this is correct
Multiple instances provide redundancy.
- ✗
Use a single Availability Zone for simplicity.
Why it's wrong here
Single AZ is not resilient.
- ✓
Enable auto-scaling to automatically replace unhealthy instances.
Why this is correct
Auto-scaling maintains desired instance count.
Visual reference
Go deeper
Related to this question
About these practice questions
One of 1,672 original MLS-C01 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
Same concept, more angles
1 more way this is tested on MLS-C01
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. A company is deploying a SageMaker model for real-time inference. The endpoint must be highly available and cost-effective. Which TWO actions should the company take? (Select TWO.)
medium- A.Use managed spot training for inference
- ✓ B.Deploy the endpoint with at least two instances in different Availability Zones
- C.Use GPU instances for all models even if not required
- ✓ D.Configure automatic scaling based on latency or request count
- E.Use a single large instance to handle peak load
Why B: Deploying a SageMaker endpoint with at least two instances in different Availability Zones (AZs) ensures high availability by eliminating a single point of failure. If one AZ goes down, traffic is automatically routed to the healthy instance in the other AZ, meeting the requirement for a highly available real-time inference endpoint.
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This MLS-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 MLS-C01 exam.