DoorDash Engineering Blog

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

Subscribe for weekly updates

Machine Learning

Using a Human-in-the-Loop to Overcome the Cold Start Problem in Menu Item Tagging

Learn how we built a classification model quickly, cheaply, and at scale

Abhi Ramachandran

Four Challenges When Launching a Product Partnership

From a product engineering perspective, external partnerships can be tricky. Here are four best practices to follow.

Manori Thakur

A Framework For Speedy and Scalable Development Of Android UI Tests

Learn how a Fluent design pattern can help create easy to read, scaleable, automated UI tests for Android development

Nishant Soni

Building Reliable Workflows: Cadence as a Fallback for Event-Driven Processing

Reengineering our event-driven delivery service for DoorDash Drive into Kotlin, we added the open source Cadence as a fallback for retries.

Alan Lin

Scaling DoorDash’s Geospatial Innovation with a Location-Based Delivery Simulator

Learn how we built a discrete event simulator for location data tests

Janice Lee

Avoiding Conditional Navigation Pitfalls When Implementing the Android Navigation Library

Learn how we we were able to utilize the Android Navigation library without sacrificing user experience

Maria Sharkina
Machine Learning

Optimizing DoorDash’s Marketing Spend with Machine Learning

Learn how we utilized cost curves to automate our marketing campaigns at scale

Aman Dhesi
Backend General

Scaling Splunk Securely by Building a Custom Terraform Provider

Ensure your growing team can search, analyze, and visualize data securely by integrating Splunk with a custom built Terraform provider.

Esha Mallya
Backend Data Machine Learning

Enabling Efficient Machine Learning Model Serving by Minimizing Network Overheads with gRPC

Learn the challenges of reducing network overheads with gRPC optimizations

Data Machine Learning

Meet Sibyl – DoorDash’s New Prediction Service – Learn about its Ideation, Implementation and Rollout

Learn how building a prediction service enables the utilization of ML models based on real-time data

Cody Zeng
Culture General

How DoorDash is Scaling its Merchant Engineering Teams to Meet New Challenges

Learn how the DoorDash merchant team has scaled up to support merchants during the Covid-19 crisis

Varsha Dudani Yvette Martinez
Machine Learning

Improving Experimental Power through Control Using Predictions as Covariate (CUPAC)

Too much varience can reducing experimental power. Learn how we solved this problem with our new CUPAC method

Jeff Li Yixin Tang Jared Bauman

Sign up for updates

Thank you for subscribing!

Sign up for updates