---
title: "Offline LLMs, Online Personalization: Generating carousels at DoorDash"
url: https://daily.dev/posts/offline-llms-online-personalization-generating-carousels-at-doordash-6e4ou6tbm
source_url: https://careersatdoordash.com/blog/doordash-offline-llms-online-personalization-generating-carousels
type: article
source: "Doordash"
published: 2026-05-27T16:03:08.207Z
updated: 2026-05-27T20:03:50.848Z
tags: ["llm", "vector-search", "recommendation-systems"]
reading_time: 20
upvotes: 0
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Offline LLMs, Online Personalization: Generating carousels at DoorDash

**[Doordash](https://daily.dev/sources/doordash)** · 20 min read · 0 upvotes · 0 comments

## Summary

DoorDash describes a production framework for generating hyper-personalized grocery store carousels using LLMs offline, avoiding inline LLM latency. The system uses a structured 'consumer memory block' as typed input to batch LLM calls that produce carousel definitions (titles, subtitles, search intents). Generated intents are embedded and stored in Milvus, then served at request time via hybrid retrieval combining embedding-based retrieval (EBR) and structured taxonomy lookup — with no LLM in the request path. Key engineering decisions include sharded Metaflow batch pipelines for millions of consumers, blue/green Milvus collection swaps for zero-downtime refreshes, per-use-case memory block trimming to reduce token cost and improve quality, and an LLM-as-judge offline eval framework that treats prompt changes like versioned model artifacts with CI. A/B results showed ~1% relative increase in pet product order rate and $0.47 increase in per-user spend over three weeks.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://careersatdoordash.com/blog/doordash-offline-llms-online-personalization-generating-carousels>

## Similar posts on daily.dev

- [Using LLMs to build content embeddings for DoorDash search and recommendations](https://daily.dev/posts/using-llms-to-build-content-embeddings-for-doordash-search-and-recommendations-fuy4zkqul) · Doordash · 0 upvotes · 0 comments
- [Building a unified consumer memory for personalization at scale](https://daily.dev/posts/building-a-unified-consumer-memory-for-personalization-at-scale-emiywz2l0) · Doordash · 0 upvotes · 0 comments
- [Bridging Affordability, Familiarity, and Novelty: DoorDash’s LLM-assisted personalization framework](https://daily.dev/posts/bridging-affordability-familiarity-and-novelty-doordash-s-llm-assisted-personalization-framework-szl0rq8ml) · Doordash · 0 upvotes · 0 comments
- [Using LLMs to infer grocery preferences from DoorDash restaurant orders](https://daily.dev/posts/using-llms-to-infer-grocery-preferences-from-doordash-restaurant-orders-ig7ur8p29) · Doordash · 1 upvotes · 0 comments
- [When GenAI Meets Personalization: Powering DoorDash’s next-generation homepage experience](https://daily.dev/posts/when-genai-meets-personalization-powering-doordash-s-next-generation-homepage-experience-cep1egbdk) · Doordash · 1 upvotes · 0 comments

---

Tags: [#llm](https://daily.dev/tags/llm), [#vector-search](https://daily.dev/tags/vector-search), [#recommendation-systems](https://daily.dev/tags/recommendation-systems)

[View this post on daily.dev](https://daily.dev/posts/offline-llms-online-personalization-generating-carousels-at-doordash-6e4ou6tbm)