--- title: Why DoorDash, Instacart, and Uber Eats Integrated LLMs... description: DoorDash, Instacart, and Uber Eats each integrated LLMs into their food delivery search systems differently, revealing how existing infrastructure shapes... canonical: https://daily.dev/posts/why-doordash-instacart-and-uber-eats-integrated-llms-into-search-three-different-ways-kabch9gjw twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Why DoorDash, Instacart, and Uber Eats Integrated LLMs Into Search Three Different Ways | daily.dev og:description: DoorDash, Instacart, and Uber Eats each integrated LLMs into their food delivery search systems differently, revealing how existing infrastructure shapes... og:url: https://daily.dev/posts/why-doordash-instacart-and-uber-eats-integrated-llms-into-search-three-different-ways-kabch9gjw og:image: https://api.daily.dev/og/posts/kaBcH9gJw.png og:image:alt: Why DoorDash, Instacart, and Uber Eats Integrated LLMs Into Search Three Different Ways og:image:width: 1200 og:image:height: 630 og:locale: 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. # Why DoorDash, Instacart, and Uber Eats Integrated LLMs Into Search Three Different Ways **[ByteByteGo](https://daily.dev/sources/bytebytego)** · 13 min read · 19 upvotes · 2 comments ## Summary DoorDash, Instacart, and Uber Eats each integrated LLMs into their food delivery search systems differently, revealing how existing infrastructure shapes architectural choices more than model selection does. DoorDash uses LLMs mostly offline to enrich a knowledge graph, keeping runtime retrieval classical. Instacart consolidates multiple specialized models under a unified LLM strategy, splitting head queries to an offline RAG-and-cache pipeline and tail queries to a real-time fine-tuned Llama-3-8B. Uber Eats goes deepest, fine-tuning a Qwen LLM as the embedding backbone of a two-tower retrieval system covering all verticals and languages. Key universal tradeoffs include hybrid classical+LLM systems, domain-specific fine-tuning or RAG on top of general world knowledge, and guardrails to keep outputs catalog-aligned. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community discussion Top comments from developers on daily.dev. **@khevlar** · 0 upvotes > The interesting part is that there isn't one 'correct' way to add AI to search. The best approach depends on what systems you already have. **@kartiknvj** · 0 upvotes > The split where Instacart routes head queries to an offline RAG-and-cache path and tail queries to a real-time fine-tuned model is the detail I find most reusable, since it treats latency budget as the real constraint rather than picking one architecture for everything. What stands out is that all three still bolt on guardrails to keep output catalog-aligned, which tells me the retrieval layer alone was never trusted to stay grounded. I would be curious how DoorDash keeps its offline knowledge-graph enrichment from going stale between rebuilds. ## Similar posts on daily.dev - [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 - [Building The Intent Engine: How Instacart is Revamping Query Understanding with LLMs](https://daily.dev/posts/building-the-intent-engine-how-instacart-is-revamping-query-understanding-with-llms-7wcfinvhu) · Instacart · 5 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#deep-learning](https://daily.dev/tags/deep-learning), [#nlp](https://daily.dev/tags/nlp), [#rag](https://daily.dev/tags/rag) [View this post on daily.dev](https://daily.dev/posts/why-doordash-instacart-and-uber-eats-integrated-llms-into-search-three-different-ways-kabch9gjw) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Why DoorDash, Instacart, and Uber Eats Integrated LLMs Into Search Three Different Ways","url":"https://daily.dev/posts/why-doordash-instacart-and-uber-eats-integrated-llms-into-search-three-different-ways-kabch9gjw","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/why-doordash-instacart-and-uber-eats-integrated-llms-into-search-three-different-ways-kabch9gjw"},"datePublished":"2026-07-28T15:33:56.564Z","dateModified":"2026-07-28T18:17:58.437Z","description":"DoorDash, Instacart, and Uber Eats each integrated LLMs into their food delivery search systems differently, revealing how existing infrastructure shapes...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/894556dd95663bbe59e7533d5de1befb?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/894556dd95663bbe59e7533d5de1befb?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"ByteByteGo","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"ByteByteGo","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/35be29234ee14d01a9cd049c52e12753","url":"https://daily.dev/sources/bytebytego"},"commentCount":2,"discussionUrl":"https://daily.dev/posts/why-doordash-instacart-and-uber-eats-integrated-llms-into-search-three-different-ways-kabch9gjw","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":19},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":2}],"keywords":"llm,deep-learning,nlp,rag","timeRequired":"PT13M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"ByteByteGo","item":"https://daily.dev/sources/bytebytego"},{"@type":"ListItem","position":3,"name":"Why DoorDash, Instacart, and Uber Eats Integrated LLMs Into Search Three Different Ways"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/why-doordash-instacart-and-uber-eats-integrated-llms-into-search-three-different-ways-kabch9gjw","comment":[{"@type":"Comment","text":"The interesting part is that there isn’t one ‘correct’ way to add AI to search. The best approach depends on what systems you already have.","datePublished":"2026-07-29T09:26:12.155Z","url":"https://daily.dev/posts/kaBcH9gJw#c-nCzvfTzD2","author":{"@type":"Person","name":"Lesley Edinam","url":"https://daily.dev/khevlar","image":"https://media.daily.dev/image/upload/s--I4QFMNNF--/f_auto/v1753089440/avatars/avatar_xMSmIuOOXE5TqCI1OLs4c?_a=BAMClqZW0"}},{"@type":"Comment","text":"The split where Instacart routes head queries to an offline RAG-and-cache path and tail queries to a real-time fine-tuned model is the detail I find most reusable, since it treats latency budget as the real constraint rather than picking one architecture for everything. What stands out is that all three still bolt on guardrails to keep output catalog-aligned, which tells me the retrieval layer alone was never trusted to stay grounded. I would be curious how DoorDash keeps its offline knowledge-graph enrichment from going stale between rebuilds.","datePublished":"2026-07-28T18:47:28.101Z","url":"https://daily.dev/posts/kaBcH9gJw#c-abUjU7CN5","author":{"@type":"Person","name":"kartik-nvjk","url":"https://daily.dev/kartiknvj","image":"https://media.daily.dev/image/upload/s--3gGgsVCw--/f_auto/v1781456774/avatars/avatar_TvTVeiMdkRCqWUDullFmy?_a=BAMAMiWQ0"}}]} ```