Why DoorDash, Instacart, and Uber Eats Integrated LLMs Into Search Three Different Ways
TLDR
DoorDash, Instacart, and Uber Eats each integrated large language models into their search systems using different architectural approaches: DoorDash uses LLMs mostly offline to enrich and parse queries against an existing knowledge graph, Instacart combines offline RAG caching with real-time fine-tuned models at the query understanding layer, and Uber Eats deployed a two-tower embedding system with fine-tuned Qwen models. DoorDash achieved a 30% lift in carousel trigger rates, Instacart improved query rewrite coverage from 50% to 95% with 6% reduced scroll depth on tail queries, and Uber Eats reduced latency by 34% through ANN parameter tuning plus quantization. Each company's choice depended primarily on existing infrastructure rather than model selection, establishing patterns for how LLMs integrate into production systems across different constraints.
Why it matters
DoorDash uses LLMs offline to enrich a knowledge graph, Instacart uses them at the query understanding layer, and Uber Eats fine-tuned a model into the embedding backbone of two-tower retrieval.
