Grey Skold | (former Android Video Engineer) ; Lin Wang | Android Performance Engineer; Sheng Liu | Android Performance Engineer Pinterest Android App offers a rare experience with a mix of images and videos on a two-column grid. In order to maintain a performant video experience on Android devices, we focused on: Warming up Configurations Pooling players Warming Up In order to reduce the startup latency, we establish a video network connection by sending a dummy HTTP HEAD request during the early application startup time. The same connection can be used to play future videos. Thi ..read more

Xue Xia, Software Engineer, Homefeed Ranking; Neng Gu, Software Engineer, Content & User Understanding; Dhruvil Deven Badani, Engineering Manager, Homefeed Ranking; Andrew Zhai, Software Engineer, Advanced Technologies Group Image from https://wallpapercave.com/neural-networks-wallpapers#google_vignette In this blog post, we will demonstrate how we improved Pinterest Homefeed engagement volume from a machine learning model design perspective — by leveraging realtime user action features in Homefeed recommender system. Background The Homepage of Pinterest is the one of most important surfac ..read more

Lin Wang | Android Performance Engineer Designed by AJ Oxendine | Software Engineer It’s a well-known fact for Android developers that an app’s manifest (AndroidManifest.xml) holds crucial application declarations. It is rarely monitored after being set up because we assume it hardly ever changes. At Pinterest, however, we have been actively monitoring the manifest after realizing it does change every so often. While building an app, Gradle downloads all the dependent libraries to compile and link them with the app. These dependent libraries each have their own mini manifest. During ..read more

Unlocking 16% Homefeed Engagement by Serving 100x Bigger Recommender Models Pong Eksombatchai | Software Engineer, Advanced Technology Group; Zhiyuan Zhang | Engineering Manager, ML Serving Platforms Image from https://unsplash.com/photos/vWgoeEYdtIY We enabled serving 100x larger recommender models at Pinterest by transitioning our machine learning serving from CPU to GPU — increasing Homefeed Pinner engagement by 16% through a step function improvement in model quality. In this blog post, we’ll share our optimizations to achieve this at neutral cost and latency, including optimizing individu ..read more

Nishant Roy | Engineering Manager, Ads Serving Platform Intro & Background The Pinterest ads serving platform delivered >$2.5 billion in ad spend in 2021 from thousands of advertisers. Our customer operations team receives 600+ tickets on average every month from advertisers who are looking to understand their performance on our platform. One of the most common questions we receive is why a particular advertiser/ad campaign is not fully utilizing its budget. This question requires a deep analysis of an ad recommendation system consisting of 5+ microservices, 1M+ lines of code, and ..read more

Ping-Min Lin | Software Engineer, Logging Platform At Pinterest, the Logging Platform team maintains the backbone of data ingestion infrastructure that ingests terabytes of data per day. When building the services powering these pipelines, it is extremely important that we build efficient systems considering how widespread and deep in the stack the systems are. Along our journey of continuous improvement, we’ve figured out basic but useful patterns and learnings that could be applied in general — and hopefully for you as well. MemQ: Achieving memory-efficient batch data delivery usi ..read more

Jeremy King | Sr Vice Presidente, ingeniería This article was originally published in English. Read the English version here. Hace dos años, estaba terminando mi primer año en Pinterest como Vicepresidente Sénior. Nuestras oficinas cerraron y el trabajo y la vida, como los conocíamos, cambiaron de golpe. Al adaptarnos a los cambios drásticos a nuestro alrededor, aprendimos mucho sobre el trabajo y sobre lo que no era un lugar de trabajo. Los beneficios del trabajo flexible y nuestra capacidad de ser productivos desde cualquier lugar dieron muchas ventajas a nuestros empleos, ya que se eli ..read more

Jeremy King | Senior Vice President, Engineering Two years ago, as I was closing in on my first annual “Pinniversary” as the Chief of Engineering at Pinterest, our offices closed, and work (read: life) as we knew it changed abruptly. As we all adapted to the drastic changes around us, we learned a lot about what was working and what wasn’t in the workplace. The benefits of working flexibly and our ability to be productive from anywhere empowered us to do our jobs well while eliminating long commutes and allowing us to be more present than ever before for important moments with family. We also ..read more

Mansfield Mark | Líder de herramientas de prueba móviles, calidad de métricas y herramientas de prueba This article was originally published in English. Read the English version here. Resumen En nuestros esfuerzos por cambiar a la izquierda (en los que las pruebas se hacen antes o se desplazan a la izquierda en la cronología del proyecto), en este blog se explica cómo empezamos a ejecutar un gran conjunto de pruebas de interfaz de usuario de extremo a extremo antes de cualquier asignación a nuestros repositorios de Android o iOS. Este proyecto involucró una cuidadosa coordinación de ..read more

Kevin Jiang | ingeniero de software de inteligencia de anuncios; Keshava Subramanya | gerente de ingeniería de inteligencia de anuncios; and Yeming Shi | ingeniera de software de inteligencia de anuncios This article was originally published in English. Read the English version here. Introducción Pinterest es un motor de descubrimiento visual que ayuda a los usuarios a encontrar ideas inspiradoras. Los anunciantes usan Pinterest para conectar con los usuarios en estas búsquedas de inspiración y su objetivo es promocionar productos o servicios de manera eficiente. El equipo de Intelig ..read more