Netflix Engineering Blog & Tech Articles
Global streaming entertainment service building innovative technology for content delivery, recommendation systems, and cloud infrastructure at scale
565 engineering articles, tutorials, and technical insights from Netflix's engineering team
Top Technologies
Latest Articles
Filter:
Netflix introduces Spin, a new feature in Metaflow 2.
Netflix Technology Blog
10 min read
Includes Code
Has Summary
--
Netflix introduces Advantage-Weighted Supervised Fine-Tuning (A-SFT), a novel post-training algorithm for generative recommender systems that addresses the unique challenges of applying reinforceme...
Netflix Technology Blog
12 min read
Has Summary
--
Netflix engineered a real-time recommendation delivery system for live events that can update over 100 million devices in under a minute.
Netflix Technology Blog
9 min read
Has Summary
--
Netflix built a Real-Time Distributed Graph (RDG) to connect member interaction data across their expanding business verticals including streaming, live events, and mobile games.
Netflix Technology Blog
8 min read
Has Summary
--
Netflix redesigned Maestro's internal workflow engine, replacing the legacy Conductor 2. x-based stateless worker model with a custom stateful actor model built on Java 21 virtual threads.
This article discusses how Netflix built a resilient data platform using a Write-Ahead Log (WAL) to address data consistency, reliability, and operational efficiency challenges at scale.
The article discusses how Netflix scales its Muse application to provide data-driven creative insights at a massive scale, focusing on the architectural evolution and optimizations made to handle t...
Netflix Technology Blog
10 min read
Includes Code
Has Summary
--
The article discusses Netflix's transformation of incident management from a centralized function to a democratized practice, emphasizing the importance of reliability in delivering seamless entert...
Netflix Technology Blog
7 min read
Has Summary
--
This article discusses the development of a reliable cloud live streaming pipeline for Netflix, focusing on the challenges faced and solutions implemented to ensure high-quality live streaming expe...
The article discusses the evolution of Netflix's client-server GraphQL APIs, focusing on how they enable dynamic page updates for personalized user experiences.
Netflix Technology Blog
14 min read
Includes Code
Has Summary
--
The article discusses the evolution of data engineering at Netflix, focusing on the introduction of Media ML Data Engineering, which aims to enhance the handling of complex media data for machine l...
Netflix Technology Blog
7 min read
Has Summary
--
The article discusses the significance of ML observability at Netflix, emphasizing its role in monitoring and understanding machine learning models, particularly in payment processing.
Netflix Technology Blog
10 min read
Has Summary
--
The article discusses how Netflix has developed an automated quality control method for video content that detects pixel-level artifacts, significantly reducing the need for manual reviews.
Netflix Technology Blog
6 min read
Has Summary
--
The article discusses Netflix's journey in implementing live streaming technology over the past three years, detailing the architectural decisions, challenges, and innovations that have led to succ...
The article discusses the evolution of Netflix's Tudum architecture, transitioning from a CQRS model utilizing Kafka to a more efficient system based on RAW Hollow.
The article discusses the implementation of AV1 Film Grain Synthesis (FGS) at scale, highlighting its significance in preserving film grain integrity while optimizing data efficiency for streaming.
Netflix Technology Blog
9 min read
Has Summary
--
The article discusses how Netflix enhances content delivery efficiency by classifying cache misses within its Open Connect content delivery network (CDN).
The article discusses Netflix's Unified Data Architecture (UDA), which aims to streamline data modeling across its various platforms by allowing teams to define business concepts once and use them ...
FM-Intent is a novel recommendation model developed by Netflix that enhances user session intent prediction through hierarchical multi-task learning.
Netflix Technology Blog
9 min read
Has Summary
--
The article discusses the architectural evolution and technical decisions involved in building a robust Ads event processing pipeline at Netflix.
Netflix Technology Blog
10 min read
Has Summary
--
The article discusses Netflix's efforts to enhance dialogue intelligibility in its content through the development of the Dialogue Integrity Pipeline.
Netflix Technology Blog
6 min read
Has Summary
--
This article discusses how Netflix accurately attributes eBPF flow logs to workload identities, addressing challenges related to misattribution in cloud environments.
Netflix Technology Blog
12 min read
Includes Code
Has Summary
--
The article discusses Netflix's Media Production Suite (MPS), a cloud-based solution designed to streamline media management in film and television production.
Netflix has begun streaming HDR10+ content for AV1-enabled devices, enhancing picture quality with dynamic metadata.
Netflix Technology Blog
6 min read
Has Summary
--
The article discusses Netflix's development of a Foundation Model for Personalized Recommendation, which aims to centralize member preference learning and enhance the efficiency of their recommenda...
Netflix Technology Blog
13 min read
Has Summary
--
The article discusses the implementation of title launch observability at Netflix, detailing the strategies, tools, and methodologies used to achieve comprehensive observability at scale.
Netflix Technology Blog
8 min read
Has Summary
--
The article discusses the implementation of a system at Netflix for tracking 'impressions'—the visual elements users interact with while browsing content.
Netflix Technology Blog
7 min read
Has Summary
--
This article is the final installment of a series on Analytics Engineering at Netflix, focusing on technical aspects and best practices for dashboard design and API deployment.
This article is the second part of a series detailing Analytics Engineering work at Netflix, focusing on various analytics applications, particularly in the context of Netflix Games.
Netflix Technology Blog
11 min read
Has Summary
--
The article introduces the new Config feature in Metaflow, which allows users to configure all aspects of their flows, particularly decorators, prior to execution.
Netflix Technology Blog
15 min read
Includes Code
Has Summary
--
The article discusses Netflix's approach to enhancing cloud efficiency through the use of Amazon Web Services (AWS) and a structured data framework.
This article is the first in a multi-part series that explores the Analytics Engineering work at Netflix, highlighting how the company empowers its teams to produce and deliver actionable analytic ...
This article discusses Netflix's Distributed Counter Abstraction, a service designed to enable distributed counting at scale while maintaining low latency performance.
The article investigates a latency issue in the Workbench UI at Netflix, specifically focusing on JupyterLab performance when running certain notebooks.
Netflix Technology Blog
14 min read
Includes Code
Has Summary
--
Netflix's TimeSeries Data Abstraction Layer is designed to efficiently store and query vast amounts of temporal event data with low latency.
Netflix Technology Blog
22 min read
Includes Code
Has Summary
--
Netflix's Key-Value Data Abstraction Layer (KV DAL) enhances data access across its distributed databases, addressing challenges in consistency, durability, and performance.
The article discusses how Netflix's Compute and Performance Engineering teams utilized eBPF for continuous, low-overhead monitoring of the Linux scheduler to detect noisy neighbor issues in their m...
Netflix Technology Blog
10 min read
Includes Code
Has Summary
--
The article discusses the evolution of Pushy, Netflix's WebSocket server, which has scaled to handle hundreds of millions of concurrent connections while maintaining a 99.
The article discusses Netflix's approach to enhancing long-term member satisfaction through its recommendation algorithms.
Netflix Technology Blog
9 min read
Has Summary
--
The article discusses methods for improving the understanding of proxy metrics derived from historical experiments, particularly in the context of A/B testing.
Netflix Technology Blog
7 min read
Has Summary
--
The article discusses the challenges and insights gained from deploying virtual threads in Java 21 at Netflix, particularly focusing on performance issues encountered with SpringBoot and Tomcat.
Netflix Technology Blog
12 min read
Includes Code
Has Summary
--
The article discusses Maestro, a horizontally scalable workflow orchestrator developed by Netflix for managing large-scale Data/ML workflows.
The article discusses Netflix's implementation of service-level prioritized load shedding to enhance system reliability and user experience during high traffic conditions.
The article provides a recap of the inaugural Data Engineering Open Forum held at Netflix, highlighting the importance of data engineering in facilitating data-driven decision-making.
Netflix Technology Blog
5 min read
Has Summary
--
The article introduces Video Annotator (VA), a framework designed to enhance the efficiency of building video classifiers using vision-language models and active learning techniques.
Netflix Technology Blog
6 min read
Has Summary
--
The article discusses the applications of causal inference at Netflix, highlighting the importance of experimentation and quasi-experimentation in enhancing member engagement.
Netflix Technology Blog
11 min read
Has Summary
--
This article investigates a cross-regional network performance issue at Netflix, detailing the troubleshooting process that led to identifying a Linux kernel upgrade as the root cause.
Netflix Technology Blog
13 min read
Includes Code
Has Summary
--
The article discusses the development of the Video Encoding Service (VES) as part of Netflix's Cosmos microservice architecture, detailing its design, implementation, and the lessons learned throug...
Netflix Technology Blog
13 min read
Includes Code
Has Summary
--
The article discusses the implementation of reverse search functionality within Netflix's Graph Search, which allows users to find queries that match specific documents instead of the traditional m...
Netflix Technology Blog
9 min read
Includes Code
Has Summary
--
This article discusses Netflix's approach to sequential A/B testing, particularly focusing on counting processes to monitor various metrics such as logins and title starts.
Netflix Technology Blog
8 min read
Includes Code
Has Summary
--