Search engine optimization (SEO) has been one of the biggest drivers of growth for Pinterest. However, it wasn’t always easy to find winning strategies at our scale. Traditionally, SEO tactics include trying out different known strategies and hoping for the best. You might have a good traffic day or a bad traffic day and not know what really triggered it, which often makes people think of SEO as magic rather than engineering.

One of the key ways we provide relevant and scalable solutions is through building distributed systems using machine learning. To accelerate our work in discovery and monetization, today we’re announcing the acquisition of Kosei, which includes some of the best minds in machine learning and data science.

Millions of people use Pinterest as a visual discovery tool each day. Search is one of the primary tools that drives discovery on the site and across our apps. In order to help Pinners find what they’re searching for in the most effective ways, we must understand their intentions behind search queries.

With the number of Pins in the system growing to well over 30 billion, it’s no wonder a top requested feature had been the ability to move a large number of Pins to another board and better manage them.

We pride ourselves on being a company focused first and foremost on the user experience. In order to deliver a great experience, including showing related content in the home feed, we’re building a service that’s fast and highly available. From a Pinner’s point of view, availability means how often they’ll get errors. For service owners, availability means how many minutes the service can be down without violating SLA (service level agreement). We use number of nines to measure the availability of our site and each service.

Pinterest is a data-driven company. On the Data Engineering team, we’re always considering how we can deliver data in a meaningful way to the rest of the company. To help employees analyze information quickly and better understand metrics more efficiently, we built Pinalytics, our own customizable platform for big data analytics.

We built Pinalytics with the following goals in mind:

Our vision is to help people live inspired lives. As engineer Tracy Chou wrote in her post about our employee demographics, “we only stand to improve the quality and impact of our products if the people building them are representative of the user base and reflect the same diversity of demography, culture, life experiences and interests that makes our community so vibrant.”

This past summer we launched News, a digest of recent activity of the people you follow. News was built by the Growth team in just two months, and delivered a significant impact in engagement as it helped people discover new content. Here, I outline our strategy, our metrics-driven approach to reduce project risk and the technical challenges.

Thanks to everyone who came to our Engineering Tech Talks last week at the Pinterest HQ in San Francisco, where we covered:

Mobile & Growth

Scaling user education on mobile, and a deep dive into the NUX using the Experience Framework, with engineers Dannie Chu and Wendy Lu

Monetization & Data

As we build products to eventually power Promoted Pins, it’s vital to maintain a no-fail reliable data infrastructure. Today we’re open sourcing Secor, a zero data loss log persistence service whose initial use case was to save logs produced by our monetization pipeline.