Netflix

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

Netflix engineers needed a real-time, unified view of service dependencies across their microservices architecture to enable faster troubleshooting and understand blast radius during incidents.

microservices observability
5 min
Netflix

In-House LLM Serving at Netflix

Netflix needed to deploy and serve large language models at scale within their production environment rather than relying on third-party hosted APIs, while maintaining the reliability and performance standards required for their streaming platform.

microservices ml-systems
5 min
Netflix

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

Netflix needed to generate personalized homepages at scale where every row, entity ordering, and layout element is customized per user while maintaining low latency and high relevance.

ml-systems real-time-systems
5 min
Netflix

Data Projects: Managing Data Assets at Netflix Scale

Netflix needed to manage governance, access control, and orchestration of millions of data warehouse tables and tens of thousands of scheduled workloads across their data platform.

distributed-systems databases
5 min
Netflix

How Netflix Simplified Batch Compute with Kueue

Netflix needed to simplify and standardize batch compute job queueing and scheduling while transitioning their container infrastructure to be more Kubernetes-native.

distributed-systems microservices
5 min
Netflix

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

Netflix needed to predict and mitigate risks associated with content launches to improve availability and reduce failures during high-impact release events.

observability microservices
5 min
Netflix

The Evolution of Cassandra Data Movement at Netflix

Netflix needed to consolidate multiple bespoke data movement connectors across different organizations into a unified, centralized management system for batch data movement operations.

microservices distributed-systems
5 min
Netflix

Thinking Fast & Slow for a Personalized Notification System

How to design a notification system that intelligently decides when and how to deliver personalized notifications to users with varying urgency and cognitive load requirements.

microservices real-time-systems
5 min
Netflix

From Silos to Service Topology: Why Netflix Built a Real-Time Service Map

Netflix engineers lacked a real-time, comprehensive view of service dependencies and relationships across their distributed microservices infrastructure, making incident diagnosis and troubleshooting during outages significantly slower.

microservices observability
5 min
Netflix

The Data Canary: How Netflix Validates Catalog Metadata

Netflix needed to detect and prevent corrupted catalog metadata from reaching millions of viewers in production before it impacts the streaming experience.

observability chaos-engineering
5 min
Netflix

The Evolution of Cassandra Data Movement at Netflix

Netflix needed to consolidate multiple bespoke data movement connectors for Cassandra across different engineering organizations into a unified, centralized management system.

microservices distributed-systems
5 min
Netflix

Thinking Fast & Slow for a Personalized Notification System

Netflix needed to design a personalized notification system that efficiently decides when and how to notify users with relevant content recommendations without overwhelming them or missing critical engagement opportunities.

microservices ml-systems
5 min
Netflix

From Silos to Service Topology: Why Netflix Built a Real-Time Service Map

Netflix needed a real-time, dynamic way for engineers to understand service dependencies and troubleshoot issues quickly across their complex distributed microservices infrastructure.

microservices observability
5 min
Netflix

Democratizing Machine Learning at Netflix: Building the Model Lifecycle Graph

Netflix needed to manage the lifecycle of machine learning models across multiple domains and teams at scale, moving beyond their original single-domain personalization focus.

ml-systems microservices
5 min
Netflix

Scaling ArchUnit with Nebula ArchRules

Netflix needed a way to enforce consistent architectural patterns and build standards across tens of thousands of Java repositories in their polyrepo strategy.

microservices general
5 min
Netflix

Scaling Camera File Processing at Netflix

Netflix needed to build a scalable, flexible media file processing pipeline that could handle diverse camera formats, workflows, and production requirements while maintaining quick turnaround times for global content production.

microservices distributed-systems
5 min
Netflix

State of Routing in Model Serving

Netflix needed to design a domain-independent traffic routing system for their ML model serving infrastructure that could handle personalized experiences at scale across multiple domains while maintaining high availability.

microservices load-balancing
5 min
Netflix

The Human Infrastructure: How Netflix Built the Operations Layer Behind Live at Scale

Netflix needed to build reliable operations infrastructure to support live streaming at massive scale, going from one show per month to nine shows per day with tens of millions of concurrent viewers.

microservices observability
5 min
Netflix

How Temporal Powers Reliable Cloud Operations at Netflix

Netflix needed reliable orchestration for business-critical cloud operations across teams like Open Connect CDN and Live reliability, but faced operational challenges as Temporal adoption grew since 2021.

distributed-systems microservices
5 min
Netflix

MediaFM: The Multimodal AI Foundation for Media Understanding at Netflix

Netflix needed scalable, deep machine-level understanding of every piece of content across an expanding catalog (including live events and podcasts) to power recommendations and discovery, but building separate models per content type and modality doesn't scale.

ml-systems microservices
5 min
Netflix

Mount Mayhem at Netflix: Scaling Containers on Modern CPUs

Netflix needed to spin up hundreds of containers in seconds to serve streaming traffic, but after modernizing their container runtime, they hit an unexpected performance bottleneck rooted in CPU architecture that impaired container scaling efficiency.

distributed-systems real-time-systems
5 min
Netflix

Optimizing Recommendation Systems with JDK’s Vector API

Netflix's Ranker service had a video serendipity scoring feature (computing how different a title is from a user's watch history) consuming ~7.5% of total CPU per node, creating a significant performance bottleneck at their enormous scale.

ml-systems real-time-systems
5 min