Company

DoorDash

61 cases from DoorDash (Food delivery, Marketplace, Adtech), each digested from a public talk or engineering post and linked to the original. 17 were checked in an online A/B test; 23 report results in production.

Tasks: Evaluate models, Recommend to new users and new items, Get experiment results faster, Rank search results, Avoid false wins in A/B tests and 18 more. Methods: LLM-as-a-judge, A/B test, Human in the loop, RAG, Gradient boosting, Multi-task learning and 118 more. Tools: LightGBM, Apache Spark, statsmodels, Elasticsearch, Qwen, Amazon S3 and 37 more.

Tech blog: careersatdoordash.com

Inside Vera, DoorDash’s Data Agentfood-delivery2026-09
Building Food Metadata with LLM Juries, Context Optimization & Multimodal AIfood-delivery2026-07
Building Ask DoorDash (Part 3): Evaluationfood-delivery2026-06
Building a unified consumer memory for personalization at scalefood-delivery2026-06
Inside DoorDash’s one-click simulation and evaluation platform for support chatbotsfood-delivery2026-06
LLM-as-a-Judge: Evaluating natural language searchfood-delivery2026-05
Using LLMs to build content embeddings for search and recommendationsfood-delivery2026-04
DashCLIP: Leveraging multimodal models for generating semantic embeddingsfood-delivery2026-02
A Simulation and Evaluation Flywheel to Develop LLM Chatbotsfood-delivery2026-01
Smarter promotions with causal machine learningfood-delivery2025-12
Accelerating experimentation at DoorDash with a multi-armed bandit platformfood-delivery2025-12
Mind the Gap: Using LLMs to bridge behavioral silos in multi-vertical recommendationsfood-delivery2025-12
When GenAI Meets Personalization: Powering DoorDash's next-generation homepage experiencefood-delivery2025-12
SafeChat: DoorDash's AI-powered safety featurefood-delivery2025-10
DoorDash: an LLM-assisted personalization framework balancing familiarity, affordability and noveltyretail2025-10
Using LLMs to infer grocery preferences from DoorDash restaurant ordersfood-delivery2025-09
How DoorDash Ads keep consumers first with budget A/B experimentationadtech2025-09
Building an anomaly detection platform at DoorDash to catch fraud trends earlyfood-delivery2025-09
A scalable LLM approach to enhancing chatbot knowledge with user-generated contentfood-delivery2025-08
Profile Generation with LLMs: Understanding consumers, merchants, and itemsfood-delivery2025-07
Advancing Menu Content with AI: How DoorDash uses AI to generate menu descriptionsfood-delivery2025-06
How DoorDash leverages LLMs to evaluate search result pagesfood-delivery2025-04
Using LLM to transcribe restaurant menu photosfood-delivery2025-03
How to investigate the online vs offline performance for DNN modelsfood-delivery2024-12
How DoorDash leverages LLMs for better search retrievalfood-delivery2024-11
Unleashing the power of large language models at DoorDash for a seamless shopping adventurefood-delivery2024-10
Part 1: DoorDash 2024 summer intern projectsfood-delivery2024-10
Precision in Motion: Deep learning for smarter ETA predictionsfood-delivery2024-10
Path to high-quality LLM-based Dasher support automationfood-delivery2024-09
How DoorDash is pushing experimentation boundaries with interleaving designsfood-delivery2024-08
Safeguarding app health and consumer experience with metric-aware rolloutsfood-delivery2024-07
Beyond the Click: Elevating DoorDash's personalized notification experience with GNN recommendationfood-delivery2024-06
Sharpening the Blur: Removing dilution to maximize experiment powerfood-delivery2024-05
Building DoorDash's product knowledge graph with large language modelsfood-delivery2024-04
Improving ETAs with multi-task models, deep learning, and probabilistic forecastsfood-delivery2024-03
Experiment Faster and with Less Effortfood-delivery2024-02
Personalizing the DoorDash Retail Store Page Experiencefood-delivery2023-12
Leveraging Flink to Detect User Sessions and Engage DoorDash Consumers with Real-Time Notificationsfood-delivery2023-11
Addressing the Challenges of Sample Ratio Mismatch in A/B Testingfood-delivery2023-10
How DoorDash Improves Holiday Predictions via Cascade ML Approachfood-delivery2023-08
How DoorDash Built an Ensemble Learning Model for Time Series Forecastingfood-delivery2023-06
Using Metrics Layer to Standardize and Scale Experimentation at DoorDashfood-delivery2023-04
Lifecycle of a Successful ML Product: Reducing Dasher Wait Timesfood-delivery2023-02
How DoorDash Upgraded a Heuristic with ML to Save Thousands of Canceled Ordersfood-delivery2023-01
Selecting the Best Image for Each Merchant Using Exploration and Machine Learningfood-delivery2023-01
Balancing Velocity and Confidence in Experimentationfood-delivery2022-11
Adapted Switch-back Testing to Quantify Incrementality for App Marketplace Search Adsfood-delivery2022-11
2022 DoorDash Summer Intern Projects Article #2food-delivery2022-10
Augmenting Fuzzy Matching with Human Review to Maximize Precision and Recalladtech2022-10
Homepage Recommendation with Exploitation and Explorationfood-delivery2022-10