Improving data processing efficiency using partial deserialization of Thrift

At Pinterest we’ve worked to greatly improve data processing efficiency. One quote that resonates with our unique approach is from writer Antoine de Saint-Exupéry: “Perfection is achieved, not when there is nothing more to add, but when there is nothing left to take away.” Ultimately…

Automating Shop The Look on Pinterest

Every day, people come to Pinterest to discover new ideas — and when they find a product they want to buy, it should be easy to purchase it. In home decor specifically, millions of people come to Pinterest to find inspiration. That’s why in 2017…

Improving HBase backup efficiency at Pinterest

Pinterest has one of the largest HBase production deployments in the industry. HBase is one of the foundational building blocks of our infrastructure and powers many of our critical services including our graph database (Zen), our general-purpose key-value store (UMS), our…

Secret management in multi-tenant environments

Knox, Pinterest’s open-source secret management service, now supports SPIFFE x509 identity documents as an authentication method. This update enables Knox to manage secrets in multi-tenant environments like Kubernetes. Knox is widely used across Pinterest’s infrastructure to provision secrets into production systems. In an…

Pre-Submit Integration Tests For Ads-Serving

Introduction & Background The ads-serving platform is the highest-scale, highest-complexity, and highest-velocity recommendation service at Pinterest. Our ads business is growing and expanding, and the ads engineering team is iterating quickly to continue to improve the system. Therefore, it is vital to keep the system healthy, in order…

HierTCN: Deep learning models for dynamic recommendations and inferring user interests

As we build a visual discovery engine, it’s crucial to understand user intent and serve relevant content through recommender systems that constantly learn from a cross-section of data to dynamically predict the next idea a Pinner will love. However, we found…

Using machine learning to auto-organize boards

While planning one’s life might look different these days, our insights tell us people are saving ideas for the future more than ever. Last month, for instance, Pinterest had a 60% increase in the number…

Pin it to Win it: Our First Virtual Pinternship

When our University Recruitment team started planning for the 2020 Pinterns to arrive, our goal was to welcome them to Pinterest and provide them with a memorable experience. As the pandemic quickly changed everyone’s plans, this core goal remained the same and we adapted our strategy to accommodate the…

Optimizing Kafka for the cloud

Takeaways Developing locality aware systems and balancing algorithms can help substantially reduce cost Making Kafka Producer and Consumer rack aware helps efficiently route traffic Data-driven engineering decision making is critical to continuously improve systems One of the fundamental principles when operating in the…

Managing Videos on Android

Video launched on the Pinterest Android app in 2016 with the goal of bringing a seamless video experience to the app. This included the ability to support multiple videos per screen, while dynamically controlling their playback state by automatically pausing them when they’ve scrolled…

PinText: A Multitask Text Embedding System in Pinterest

Word embeddings have been actively studied and developed by researchers and practitioners in the machine learning community since the neural network language model was proposed. Researchers not only proposed principled algorithms and open-source code, but they also released pre-trained embedding models with public…

A Pinterest Engineering guide to technical interviews

Technical interviews are the key component to landing an engineering role. Everything from preparation to asking the right questions is important for a successful interview. In this post, Pinterest employees from Recruiting and Engineering share tips and tricks for…

The top Pinterest Engineering blog posts of 2018

The most-read posts of the year Three-day no-meeting schedule for engineers A one year PWA retrospective Supporting React Native How Pinterest runs Kafka at scale How switching our domain structure unlocked international growth PinSage: A new graph convolutional neural network for web-scale recommender systems Looking inside the technology that powers Pinterest Building a more inclusive way to search Building a real-time user action counting system for ads Goku: Building a scalable and high performant time series database system We’ll be back in 2019 with more updates from the team. Happy New Year!

Improving the Quality of Recommended Pins with Lightweight Ranking

The Pinterest corpus is composed of billions of Pins, however, each Pinner only sees a small subset based on their interests when…

PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest

As we build a visual discovery engine that powers 2B+ Pins, it’s crucial to understand user interests and preferences in…

Cómo redujimos el tamaño de la aplicación de Pinterest para iOS en más de un 30% / 50 MB

This blog was originally published in English. To read the English version, click here. Todos sabemos que el tamaño de las aplicaciones es importante (el tamaño de descarga[1] y el tamaño de instalación local[2]). Además, existe una correlación…

Building interactive email with AMP

AMP (Accelerated Mobile Pages) is an open source technology created by Google to support fast mobile web pages. Over the years, we’ve partnered with Google and adopted AMP technology in our mobile web pages to deliver a faster, more efficient user experience. Most…

Pinterest + ktlint = ❤

Ha pasado casi un año desde que la base de código Android de Pinterest se convirtió en la prioridad de Kotlin, y aproximadamente dos años desde que adoptamos ktlint para el formato y lint de Kotlin. Hoy, compartimos que Pinterest se…

Understanding the product cycle of discovery to purchase on Pinterest

Pinners have always used Pinterest for shopping, as they often come in a planning mindset and are exploring products and…

Goku: Building a scalable and high performant time series database system

Co-authored by Jinghan Xu, Jian Wang & Tian-Ying Chang, Engineers At Pinterest, developers rely on Statsboard to monitor their systems and discover issues. A reliable and efficient monitoring system is very important for development velocity. Historically, we’ve used OpenTSDB to ingest and…

Building a real-time user action counting system for ads

The Pinterest ads team’s mission is to provide the best experience for both Pinners and advertisers. Our ads system is a real-time bidding system that delivers targeted ads based on a variety of attributes. One…

Using graph algorithms to optimize Kafka operations, Part 1

Pinterest uses Kafka across the board for data movement. The Logging Platform team alone manages over 3,000 Kafka brokers transporting trillions of messages per day to help bring more than 320 million monthly active Pinners the inspiration to create a life they love. …

Partitioning Pinlater for Fun(?) and Profit(!)

Contained within the November 2015 announcement of the open-sourcing of Pinlater, our asynchronous job execution system, was a description of some of the improvements that had been made to the system since the original 2014 blog post describing its creation. Notable among…

User state-based notification volume optimization

Notifications play an important role in helping Pinterest’s 335M+ monthly active users discover and engage with inspiring content. It’s crucial to send the right number of notifications with high quality content. If we send too few notifications, Pinners might miss out on great opportunities…

What we learned from an iOS app OOMs incident

In early 2020, we started seeing significantly elevated out-of-memory (OOM) crashes in the Pinterest iOS app. That incident resulted in a declined Crash-Free Users Rate (CFUR), from the previous 99% to 96%, which was a steep drop. What was going on? We improved…