An ML engineer needs to use Amazon SageMaker to fine-tune a large language model (LLM) for text summarization. The ML engineer must follow a low-code no-code (LCNC) approach. Which solution will meet

Question

Options

• AUse SageMaker Studio to fine-tune an LLM that is deployed on Amazon EC2 instances.
• BUse SageMaker Autopilot to fine-tune an LLM that is deployed by a custom API endpoint.
• CUse SageMaker Autopilot to fine-tune an LLM that is deployed on Amazon EC2 instances.
• DUse SageMaker Autopilot to fine-tune an LLM that is deployed by SageMaker JumpStart.

• A
  3% (1)
• B
  6% (2)
• C
  11% (4)
• D
  81% (29)

Explanation

Option D is correct because SageMaker Autopilot provides the automated, low-code/no-code AutoML experience, and SageMaker JumpStart is the managed hub for pre-built foundation models - together they allow an ML engineer to fine-tune an LLM entirely through a UI without writing custom code or managing infrastructure.

Option A is wrong on two counts: SageMaker Studio is a full developer IDE (inherently code-heavy), and deploying on raw EC2 instances requires manual infrastructure management - neither is LCNC.

Option B is wrong because a "custom API endpoint" implies writing and maintaining custom integration code, which violates the LCNC requirement regardless of what tool handles the training.

Option C is wrong for the same infrastructure reason as A - deploying directly onto EC2 instances forces the engineer to manage servers manually, which is the opposite of LCNC.

Memory tip: Associate JumpStart with "jump-starting without code" - it's SageMaker's curated model hub where you pick an LLM and fine-tune it through point-and-click. Whenever you see LCNC + LLM + SageMaker, JumpStart is the answer; EC2 and custom endpoints are "bring your own code" signals that rule out LCNC.

No community discussion yet for this question.