DoorDash Engineering Blog

Learn about high impact projects that power our velocity, reliability, and innovation.

Featured Article

Backend Minimizing Risk for API Extraction in a Major Migration Project

DoorDash engineering describes its three step process for safely migrating business logic as APIs.

David Chen

8 Minute Read

Data Machine Learning

Building a Gigascale ML Feature Store with Redis, Binary Serialization, String Hashing, and Compression

When a company with millions of consumers such as DoorDash builds machine learning (ML) models, the amount of feature data can grow to billions of records with millions actively retrieved during model inference under low latency constraints. These challenges warrant a deeper look into selection and design of a feature store — the system responsible ...

Uncovering Online Delivery Menu Best Practices with Machine Learning

Learn how we analyzed over 100K online delivery menus to develop menu best practices

Hello Seattle: DoorDash Expands its Engineering Footprint to the Pacific Northwest

DoorDash opens a new tech office in Seattle to support its Drive and DashMart business lines.

Hot Swapping Production Tables for Safe Database Backfills

DoorDash engineering explains how to edit large data tables safely and quickly in a production database.

Building an Image Upload Endpoint in a gRPC and Kotlin Stack

Learn how we automated image uploads in gRPC and Kotlin

Solving for Unobserved Data in a Regression Model Using a Simple Data Adjustment

Learn how our team optimized prep time estimates while overcoming censored data

Using Display Modules to Enable Rapid Experimentation on DoorDash’s Homepage

Learn how a flexible UI that utilized display modules enabled rapid experimentation

Improving Online Experiment Capacity by 4X with Parallelization and Increased Sensitivity

To speed up the development of new features we needed a way to increase our experiment capacity. Learn how we improved it by 4X

Integrating a Search Ranking Model into a Prediction Service

Learn how moving ML models to a prediction service can free up RAM and CPU for more scalable development

Building the Caviar Web Experience Using Reusable React Components on the DoorDash Platform

After DoorDash's acquisition of Caviar, we revised our web architecture to run two experiences off one platform.

How DoorDash is Scaling its Data Platform to Delight Customers and Meet our Growing Demand

Learn the challenges and best practices to successfully growing a data platform organization

Leveraging Causal Modeling to Get More Value from Flat Experiment Results

Using Heterogeneous Treatment Effects to improve personalization