Browse past weeks of engineering reads.
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.
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.
Building a data analysis system that can reliably infer causal relationships from observational data while accounting for hidden biases and confounding variables that automated agents might miss.
Netflix needed to predict and mitigate risks associated with content launches to improve availability and reduce failures during high-impact release events.
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.
Netflix needed to enable video editors to have more fine-grained control and predictability over AI-assisted video editing systems for creating promotional content at scale.
Netflix needed to improve the accuracy of video quality assessment metrics beyond VMAF v0 to make better encoding decisions and prevent quality misjudgments that could degrade the member experience.
Building a reliable causal inference system that can accurately determine cause-and-effect relationships in data (like the impact of a show on retention) while accounting for hidden biases and confounding variables that automated agents might miss.
Netflix needed to predict and mitigate risks associated with content launches to improve reliability and reduce unexpected failures in production.
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.
Accurately measuring video quality perception to optimize encoding decisions and ensure Netflix members receive the best possible streaming experience across different bitrates and codecs.
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.
Netflix needed to automatically evaluate the quality and relevance of show synopses at scale to improve member discovery and engagement.
Netflix needed to efficiently extract and surface key moments from hundreds or thousands of hours of raw video footage for editorial teams to accelerate the creative content production process.
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.
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.
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.
Generic pre-trained LLMs lack the domain-specific alignment needed for Netflix's production use cases in recommendation, personalization, and search, and the post-training pipeline to fine-tune them doesn't scale efficiently across multiple domain constraints and reliability requirements.
Netflix's Graph Search platform for federated enterprise data required users to write structured queries, limiting accessibility and ease of use despite the system being scalable and configurable.