Why it matters
Raghav Saboo describes DoorDash’s use of offline LLM reasoning to improve fast retrieval and ranking systems. Graded relevance labels distinguish a shopper’s constraints from popularity, while a second training stage targets difficult examples. Semantic IDs and reusable consumer memory support recommendations and generated collections. The architecture is concrete; reported business and ranking gains remain specific to the experiments described.
My takeaway: Test constraint satisfaction separately from engagement. Audit generated labels, mine difficult retrieval cases and measure freshness, latency and quality before moving expensive inference into an offline pipeline.