ecommerce_ops · workflow

DoorDash redesigns explore page Feed Service with a DAG-based pipeline pattern, achieving 35% latency reduction and 60% CPU reduction

DoorDash's explore page Feed Service made repeated, duplicative calls to downstream services for every carousel, could rank only within a single carousel rather than across the page, and lacked modularization — causing development overhead to grow proportionally with system complexity as the business scaled.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Candidate retrieval
Data sources are fetched once from external services — the Search Service for stores and the Promotion Service for carousels' metadata — to avoid duplicate calls.
Tools used
Feed ServiceSearch ServicePromotion ServiceWorkflowmachine learning prediction service
Outcome

The new pipeline achieved a 35% p95 latency reduction for the explore feed endpoint, a 60% CPU reduction from the Feed Service, an 80% QPS reduction and 50% CPU reduction from the Search Service, and an overall estimated reduction of 4,500 CPU cores, while enabling cross-carousel ranking and extending the pattern to new applications.

What failed first

The previous Feed Service architecture made duplicative downstream calls per carousel, constrained ranking to the Search Service where it could only operate within individual carousels, and required candidate generation logic to be duplicated across multiple applications with strongly overlapping functionality.

Results
Volume35%
Source

https://careersatdoordash.com/blog/pipeline-design-pattern-recommendation/

How we source this →

Grounding & classification
Source type: technical build writeup
27 fields verified against source quotes.
personalizationpredictive analyticsrecommendation systemproduct catalogfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedecommercecost reductioncycle time reductionemployee productivitytechnical build writeupecommerce opsdata sync enrichmentextract classify route