Scaling LLM Post-Training at Netflix

**Scaling LLM Post-Training at Netflix**

Baolin Li, Lingyi Liu, Binh Tang, Shaojing LiIntroductionPre-training gives Large Language Models (LLMs) broad linguistic ability and general world knowledge, but post-training is the phase that actually aligns them to concrete intents, domain constraints, and the reliability requirements of production environments. At Netflix, we are exploring how LLMs can enable new member experiences across recommendation, personalization, and search, which requires adapting generic foundation models so they can better reflect our catalog and the nuances of member interaction histories. At Netflix scale, post-training quickly becomes an engineering problem as much as a modeling one: building and operating complex data pipelines, coordinating distributed state across multi-node GPU clusters, and orchestrating workflows that interleave training and inference. This blog describes the architecture and engineering philosophy of our internal Post-Training Framework, built by the AI Platform team to hide infrastructure complexity so researchers and model developers can focus on model innovation — not distributed systems plumbing.A Model Developer’s Post-Training JourneyPost-training often starts deceptively simply: curate proprietary domain data, load an open-weight model from Hugging Face, and iterate batches through it. At the experimentation scale, that’s a few lines of code...

---

**[devsupporter 해설]**

이 기사는 Netflix Tech에서 제공하는 최신 개발 동향입니다. 관련 도구나 기술에 대해 더 알아보시려면 원본 링크를 참고하세요.