# Amazon — Build an AI-powered product tagging system with Amazon SageMaker serverless model customization

- Company: Amazon (amazon.com)
- Announced: 2026-09-15T16:11:36+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://aws.amazon.com/blogs/machine-learning/build-an-ai-powered-product-tagging-system-with-amazon-sagemaker-serverless-model-customization/
- Record: https://forck.live/items/10958-build-an-ai-powered-product-tagging-system-with-amazon-sagemaker-serverless
- Subject: Bedrock / Nova
- Models affected: Qwen3-8B

Amazon’s walkthrough customizes Qwen3-8B for product tagging with supervised fine-tuning and reinforcement learning with verifiable rewards. SageMaker serverless model customization manages training; the resulting model is deployed separately to SageMaker Asynchronous Inference.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/build-an-ai-powered-product-tagging-system-with-amazon-sagemaker-serverless-model-customization/:

> In this walkthrough, we customize Qwen3-8B with supervised fine-tuning (SFT), then optimize it with reinforcement learning with verifiable rewards (RLVR) using Group Relative Policy Optimization (GRPO). Amazon SageMaker serverless model customization manages the training capacity

---

Record: https://forck.live/items/10958-build-an-ai-powered-product-tagging-system-with-amazon-sagemaker-serverless
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md