Skip to content

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

Amid the hypergrowth of DoorDash’s business, we found the need to reengineer our platform, extracting business lines from a Python-based monolith to a microservices-based architecture in order to meet our scalability and reliability needs.

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

At DoorDash, we confronted similar issues in our gRPC-based model serving setup for search ranking with network overheads taking up to 50 percent of service response time.

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

As companies utilize data to optimize and personalize customer experiences, it becomes increasingly important to implement services that can run machine learning models on massive amounts of data to quickly generate large-scale predictions.

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

On the front lines of addressing Stay-At-Home orders caused by the COVID-19 pandemic, DoorDash’s Merchant team has been busy ensuring that merchants have what they need to offer delivery, get onboarded onto the platform and that everything is scaled to maximize reliability.

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

In this post, we introduce a method we call CUPAC (Control Using Predictions As Covariates) that we successfully deployed to reduce extraneous noise in online controlled experiments, thereby accelerating our experimental velocity. 

Rapid experimentation is essential to helping DoorDash push key performance metrics forward.