AI Reports · Amazon · 2026-10-22 · Product announcement
Announcing new ways to customize models with SageMaker AI, without managing GPUs
Amazon SageMaker AI serverless model customization now includes training sessions, generally available today. Users can write and coordinate their own post-training loop, including custom loss functions, reward signals, or multi-turn reinforcement learning, while SageMaker AI handles GPU allocation, distributed execution, fault recovery, and checkpoint storage. Techniques such as SFT, DPO, RLVR, RLAIF, and multi-turn RL are supported, with a choice of LoRA or full fine-tuning and the option to chain techniques through continuous customization.