Learn about high impact projects that power our velocity, reliability, and innovation.
Focusing on delivery allowed DoorDash to build a food search engine, but expanding beyond food with more SKUs and merchants requires a substantial upgrade.
Learn about which caching libraries we considered, the analysis of our system and how we were able to use experiments to validate our approach.
When failure is inevitable, building fault tolerance with fault injection testing ensures that failures do not bring the platform down with them
Having a quality selection did not happen by accident. Learn about the ML models that power the diverse, high quality selection on our platform
We’re thrilled to welcome Liangxiao, our first VP of Engineering, to DoorDash!
Learn about the principles and big bets that enabled to scale and maintain our ML platform which supports our data users and data scientists
Which loss function is best for long tail event prediction? learn how we used gamma distributions to boost eta prediction accuracy
To quickly implement new fraud prevention "frictions" we built a common library with React.js Typescript and Apollo graph. Read the guide
Displaying enticing product images with fast load speeds on high-traffic pages can be a hard. Learn how we implemented server side rendering with next.js
Epsilon-Greedy, The Upper Confidence Bound, Thompson Sampling: which is the best Multi-armed bandit algorithm for promotion optimization?
Learn how DoorDash balanced ML models' release speed and reliability by shipping darkly in order to manage fraud model deployments
Learn how we used multi-tenancy to improve production testing standards, speed and effectiveness in this new technical blog post