A Tale of Two Flink Autoscalers
How and Why Netflix Built a Real-Time Distributed Graph: Part 3 — Querying the graph with gRPC…
In-House LLM Serving at Netflix
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
Optimizing Recommendation Systems with JDK’s Vector API
By Harshad Sane
Behind the Streams: Building a Reliable Cloud Live Streaming Pipeline for Netflix. Part 2.
By Allison Deal, Cyril Concolato, Flavio Ribeiro, Hunter Ford, Mariana Afonso, Thomas Symborski, Xiaomei Liu
Driving Content Delivery Efficiency Through Classifying Cache Misses
The mission of Open Connect, our dedicated content delivery network (CDN), is to deliver the best quality of experience (QoE) to our members. By localizing our Open Connect Appliances (OCAs), we…
How Netflix Accurately Attributes eBPF Flow Logs - Netflix TechBlog
In a previous blog post, we described how Netflix uses eBPF to capture TCP flow logs at scale for enhanced network insights. In this post, we delve deeper into how Netflix solved a core problem…
Part 3: A Survey of Analytics Engineering Work at Netflix
This article is the last in a multi-part series sharing a breadth of Analytics Engineering work at Netflix, recently presented as part of our annual internal Analytics Engineering conference. Need to…
Part 2: A Survey of Analytics Engineering Work at Netflix
This article is the second in a multi-part series sharing a breadth of Analytics Engineering work at Netflix, recently presented as part of our annual internal Analytics Engineering conference. Need…
Investigation of a Workbench UI Latency Issue - Netflix TechBlog
With special thanks to our stunning colleagues Amer Ather, Itay Dafna, Luca Pozzi, Matheus Leão, and Ye Ji. At Netflix, the Analytics and Developer Experience organization, part of the Data Platform…
Introducing Netflix’s TimeSeries Data Abstraction Layer
As Netflix continues to expand and diversify into various sectors like Video on Demand and Gaming, the ability to ingest and store vast amounts of temporal data — often reaching petabytes — with…
Pushy to the Limit: Evolving Netflix’s WebSocket proxy for the future
Pushy is Netflix’s WebSocket server that maintains persistent WebSocket connections with devices running the Netflix application. This…
Java 21 Virtual Threads - Dude, Where’s My Lock?
Getting real with virtual threads
Enhancing Netflix Reliability with Service-Level Prioritized Load Shedding
In November 2020, we introduced the concept of prioritized load shedding at the API gateway level in our blog post, Keeping Netflix Reliable Using Prioritized Load Shedding. Today, we’re excited to…
Rebuilding Netflix Video Processing Pipeline with Microservices
An introductory blog providing an overview of Netflix's new microservices-based video pipeline. Future blogs will provide deeper dives into each service, sharing insights and lessons learned from this process.
Incremental Processing using Netflix Maestro and Apache Iceberg
Incremental processing is an approach to process new or changed data in workflows. The key advantage is that it only incrementally processes data that are newly added or updated to a dataset, instead…
Streamlining Membership Data Engineering at Netflix with Psyberg | by Netflix Technology Blog | Nov, 2023 | Netflix TechBlog
At Netflix, our Membership and Finance Data Engineering team harnesses diverse data related to plans, pricing, membership life cycle, and revenue to fuel analytics, power various dashboards, and make…
Diving Deeper into Psyberg: Stateless vs Stateful Data Processing
In the inaugural blog post of this series, we introduced you to the state of our pipelines before Psyberg and the challenges with incremental processing that led us to create the Psyberg framework…
Zero Configuration Service Mesh with On-Demand Cluster Discovery
Netflix’s service mesh adoption: history, motivations, and how we worked with the Envoy community on a streamlining service mesh adoption in complex microservice environments
Curbing Connection Churn in Zuul - Netflix TechBlog
When Zuul was designed and developed, there was an inherent assumption that connections were effectively free, given we weren’t using mutual TLS (mTLS). It’s built on top of Netty, using event loops…
Detecting Scene Changes in Audiovisual Content - Netflix TechBlog
When watching a movie or an episode of a TV show, we experience a cohesive narrative that unfolds before us, often without giving much thought to the underlying structure that makes it all possible…
Migrating Critical Traffic At Scale with No Downtime — Part 2
Picture yourself enthralled by the latest episode of your beloved Netflix series, delighting in an uninterrupted, high-definition streaming experience. Behind these perfect moments of entertainment…
Improved Alerting with Atlas Streaming Eval - Netflix TechBlog
Engineers want their alerting system to be realtime, reliable, and actionable. While actionability is subjective and may vary by use-case, reliability is non-negotiable. In other words, false…
Scaling Media Machine Learning at Netflix - Netflix TechBlog
We tackle some of the unique challenges of scaling multimodal machine learning models that operate on media assets (video, audio, and text).
Data Reprocessing Pipeline in Asset Management Platform @Netflix
At Netflix, we built the asset management platform (AMP) as a centralized service to organize, store and discover the digital media assets created during the movie production. Studio applications use…
Netflix: A Culture of Learning - Netflix TechBlog
Martin Tingley with Wenjing Zheng, Simon Ejdemyr, Stephanie Lane, Colin McFarland, Mihir Tendulkar, and Travis Brooks Earlier posts in this series covered the why, what and how of A/B testing, all of…
Interpreting A/B test results: false negatives and power
This is the fourth post in a multi-part series on how Netflix uses A/B tests to inform decisions and continuously innovate on our products. Need to catch up? Have a look at Part 1 (Decision Making at…
Data pipeline asset management with Dataflow - Netflix TechBlog
The problem of managing scheduled workflows and their assets is as old as the use of cron daemon in early Unix operating systems. The design of a cron job is simple, you take some system command, you…
Practical API Design at Netflix, Part 2: Protobuf FieldMask for Mutation Operations
At Netflix, we heavily use gRPC for the purpose of backend to backend communication. This post explains how to use Protobuf FieldMask to design update and remove APIs.
Introducing Netflix Timed Text Authoring Lineage - Netflix TechBlog
Dubbing and subtitling are inherently creative processes. At Netflix, we strive to make shows as joyful to watch in every language as in the original language, whether a member watches with original…
My (Seemingly) Random Walk to Netflix - Netflix TechBlog
I am going to tell you a story about a person that works for Netflix. That person grew up dreaming of working in the entertainment industry. They attended the University of Southern California…
Achieving observability in async workflows - Netflix TechBlog
Managing and operating asynchronous workflows can be difficult without the proper tools and architecture that puts observability, debugging, and tracing at the forefront. Imagine getting paged…
Hawkins: Diving into the Reasoning Behind our Design System
by Hawkins team member Joshua Godi; with cover art from Martin Bekerman and additional imagery from Wiki Chaves
ConsoleMe: A Central Control Plane for AWS Permissions and Access | Netflix Tech Blog
ConsoleMe is a central control plane for AWS that provides an easier way to manage AWS permissions and access across multiple accounts. It encourages least-privilege access and AWS permissions.
The Netflix Cosmos Platform - Netflix TechBlog
Cosmos is a computing platform that combines the best aspects of microservices with asynchronous workflows and serverless functions. Its sweet spot is applications that involve resource-intensive…
Optimizing the Aural Experience on Android Devices with xHE-AAC
Technical information about how Netflix uses Android APIs and xHE-AAC metadata, especially MPEG-D DRC, to optimize the listening experience.
Optimizing data warehouse storage - Netflix TechBlog
At Netflix, our current data warehouse contains hundreds of Petabytes of data stored in AWS S3, and each day we ingest and create additional Petabytes. At this scale, we can gain a significant amount…
How Netflix Scales its API with GraphQL Federation (Part 2)
Learn what’s needed to migrate to and run a federated GraphQL API platform successfully.
Toward a Better Quality Metric for the Video Community
Over the past few years, we have been striving to make VMAF a more usable tool not just for Netflix, but for the video community at large. This tech blog highlights our recent progress toward this…
Keeping Netflix Reliable Using Prioritized Load Shedding
Getting stuck in traffic is one of the most frustrating experiences for drivers around the world. Everyone slows to a crawl, sometimes for a minor issue or sometimes for no reason at all. As…
Bulldozer: Batch Data Moving from Data Warehouse to Online Key-Value Stores
Netflix has more than 195 million subscribers that generate petabytes of data everyday. Data scientists and engineers collect this data from our subscribers and videos, and implement data analytics…
Unbundling Data Science Workflows with Metaflow and AWS Step Functions
by David Berg, Ravi Kiran Chirravuri, Romain Cledat, Jason Ge, Savin Goyal, Ferras Hamad, Ville Tuulos tl;dr Today, we are releasing a new job scheduler integration with AWS Step Functions. This…
Keeping Customers Streaming — The Centralized Site Reliability Practice at Netflix
We’re privileged to be in the business of bringing joy to our customers at Netflix. Whether it’s a compelling new series or an innovative product feature, we strive to provide a best-in-class service…
How Netflix uses Druid for Real-time Insights to Ensure a High-Quality Experience
Ensuring a consistently great Netflix experience while continuously pushing innovative technology updates is no easy feat. How can we be confident that updates are not harming our users? And that…
100X Faster: How We Supercharged Netflix Maestro’s Workflow Engine
A Human-Augmenting Agentic Workflow for Causal Inference
Active-Active for Multi-Regional Resiliency
Building Service Topology at Scale: Architecture, Challenges, and Lessons Learned
Caching for a Global Netflix
Empowering the Visual Effects Community with the NetFX Platform
Genie 2.0: Second Wish Granted!
GenRec: Towards LLM-Native Recommendation at Netflix
Globalizing Productions with Netflix’s Media Production Suite
HTML5 Video Playback UI
Introducing Curator — The Netflix ZooKeeper Library
