Netflix TechBlog

NetflixJul 30, 2026

GenRec: Towards LLM-Native Recommendation at Netflix

Engineers at Netflix developed GenRec, an LLM-native recommendation system that outperforms its mature production counterpart while relying on fewer labeled examples and input signals. GenRec verbalizes user histories and item metadata into text, post-trains a foundation LLM on Netflix-specific data, and adds a catalog-aware scoring head to produce personalized rankings. In a large-scale A/B test, GenRec achieved significant improvements in short-term and long-term online metrics, reducing the reliance on hand-engineered features and shifting focus from feature engineering to context engineering. The system's two-phase training framework leverages Phase 1 to adapt a foundation LLM on Netflix data and Phase 2 to post-train on ranking-specific data and objectives. GenRec training uses conversations between users and a recommender, converted from log data, to support both language-modeling and ranking objectives. The system employs verbalization and context engineering techniques to balance token budgets and ranking quality, applying rewards-weighted training to align with long-term member

StreamingScale

14 min

Latest Articles

MAPS: Netflix’s Multimodal Asset Personalization at Scale

A Tale of Two Flink Autoscalers

How and Why Netflix Built a Real-Time Distributed Graph: Part 3 — Querying the graph with gRPC…

Modeling Device Capabilities for Analytics

GenRec: Towards LLM-Native Recommendation at Netflix

In-House LLM Serving at Netflix

Building Service Topology at Scale: Architecture, Challenges, and Lessons Learned

GenPage: Towards End-to-End Generative Homepage Construction at Netflix

Toward More Controllable AI Video Editing: An Early Research Exploration at Netflix

How Netflix Simplified Batch Compute with Kueue

The Data Canary: How Netflix Validates Catalog Metadata

Data Projects: Managing Data Assets at Netflix Scale

Predicting Risk in Content Launches: How Data-Driven Insights can Transform Launch Planning

The Evolution of Cassandra Data Movement at Netflix

Thinking Fast & Slow for a Personalized Notification System

A Human-Augmenting Agentic Workflow for Causal Inference

VMAF v1: Good Is Not Good Enough

VMAF v1: Good Is Not Good Enough

A Human-Augmenting Agentic Workflow for Causal Inference

Thinking Fast & Slow for a Personalized Notification System

Netflix TechBlog

Latest Articles

MAPS: Netflix’s Multimodal Asset Personalization at Scale

A Tale of Two Flink Autoscalers

How and Why Netflix Built a Real-Time Distributed Graph: Part 3 — Querying the graph with gRPC…

Modeling Device Capabilities for Analytics

GenRec: Towards LLM-Native Recommendation at Netflix

In-House LLM Serving at Netflix

Building Service Topology at Scale: Architecture, Challenges, and Lessons Learned

GenPage: Towards End-to-End Generative Homepage Construction at Netflix

Toward More Controllable AI Video Editing: An Early Research Exploration at Netflix

How Netflix Simplified Batch Compute with Kueue

The Data Canary: How Netflix Validates Catalog Metadata

Data Projects: Managing Data Assets at Netflix Scale

Predicting Risk in Content Launches: How Data-Driven Insights can Transform Launch Planning

The Evolution of Cassandra Data Movement at Netflix

Thinking Fast & Slow for a Personalized Notification System

A Human-Augmenting Agentic Workflow for Causal Inference

VMAF v1: Good Is Not Good Enough

VMAF v1: Good Is Not Good Enough

A Human-Augmenting Agentic Workflow for Causal Inference

Thinking Fast & Slow for a Personalized Notification System