资讯与观察
AI 行业动态、工程实践、产品方法和社区故事。
An Organizational Second Brain: Building an AI That Learns From Experts
We’ve built an AI agent that acts as a secondary expert for a given domain, making deep specialist knowledge readily available and preserved for anyone in an organization to access, share, and build upon. This is not a …
MAPS: Netflix’s Multimodal Asset Personalization at Scale
By Emma Yanyang Kong, Aditya Deshpande, Asad Abbasi, Bowei Yan, David Fagnan, Ashish Rastogi, Dhaval Patel, Ray Zhang Introduction The Netflix experience is a journey of discovery. Every visual cue, from the artwork on …
30 分钟 · Netflix TechBlog
MetaRoCE: A New RDMA Transport Built for AI-Scale Ethernet
Training and serving frontier AI models depends on fast, reliable networks that move data between GPUs without wasting compute cycles. To meet this challenge at scale, Meta designed MetaRoCE – a clean-sheet RDMA transpo…
26 分钟 · Meta EngineeringLATEST STORIES
最新内容
MTIA 300: Meta’s First Training Chip with Built-in NICs and Communication-Offloading Engines精选导读
MTIA 300 is the first of Meta’s family of in-house training and inference accelerators optimized for training ranking and recommendation models. We’re sharing how MTIA 300’s built-in NIC chiplets allow it to meet the co…
A Tale of Two Flink Autoscalers精选导读
Samuel Yeboah, Francesco Di Chiara and Mingliang Liu Today, Netflix runs two Flink autoscalers. That is exactly one more than we want. We built the first one in-house years ago, when there was no mature option suited to…
How We’re Building Scam Alert on WhatsApp With End-to-End Encryption and Verifiability Guarantees精选导读
WhatsApp is committed to helping people stay safe while protecting the privacy of their messages. As scam tactics evolve — from impersonation to social engineering to AI-generated lures — we’re always evolving as well, …
How and Why Netflix Built a Real-Time Distributed Graph: Part 3 — Querying the graph with gRPC…精选导读
How and Why Netflix Built a Real-Time Distributed Graph: Part 3 — Querying the graph with gRPC execution API Authors: Nilesh Mishra and Ajit Koti This is the third entry of a multi-part blog series describing how we bui…
From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking精选导读
Every day, Meta’s recommendation platforms handle billions of user interactions, generating rich temporal signals that capture individual preferences and intent across products, ads, and content. In our 2024 post on seq…
Modeling Device Capabilities for Analytics精选导读
by Aarti Laddha, Richard Diaz-Cool, Rishika Idnani, Venkatesh Selveraj Netflix supports a vast and evolving set of features and content types, ranging from 4K streaming and immersive audio to live streaming and cloud ga…
GenRec: Towards LLM-Native Recommendation at Netflix精选导读
Authors: Ying Li, Arjun Rao, Shradha Sehgal Introduction Recommendations sit at the heart of the Netflix experience. Our current production models rely on thousands of hand‑crafted features over users, items, and intera…
In-House LLM Serving at Netflix精选导读
By AI Platform’s Model Runtime team and Inference team Introduction Most organizations consume LLMs through hosted APIs. Netflix went further — we run the full stack ourselves, from model deployment through inference, i…
Building Service Topology at Scale: Architecture, Challenges, and Lessons Learned精选导读
By Parth Jain, Rakesh Sukumar, Yingwu Zhao, Renzo Sanchez-Silva & Nathan Fisher A deep dive into the engineering challenges of building a real-time service dependency map at Netflix scale: from streaming architectures a…