2026-06-15 21:55
DoorDash is enhancing its search ad relevance using small language models (SLMs). Consumers expect ads to match their search intent seamlessly. By implementing query-item relevance prediction, DoorDash aims to ensure ads feel integrated into the search experience, rather than disruptive. Recent advancements in SLMs enable better semantic understanding and faster predictions, improving the accuracy of sponsored results. This approach addresses the challenge of matching user queries with...
Source: DoorDash Engineering
Sharat Bhat
2026-06-11 12:56
🚀 Excited to share insights from the article on DoorDash Assistant's engineering! This piece kicks off a blog series exploring the technology behind the Assistant. It focuses on how consumers can easily request meals or groceries tailored to their preferences. Key areas include local-commerce grounding and the importance of personalization. The Assistant is currently rolling out in select U.S. areas on iOS, enhancing restaurant and grocery search. Stay tuned for future updates on its...
Source: DoorDash Engineering
Hong Tai Wei
2026-06-08 21:25
🚀 DoorDash is enhancing personalization by building a unified consumer memory platform. This platform captures consumer behaviors across various marketplaces, including restaurants and retail. 📊 It systematically extracts semantic insights from data, enabling better understanding of dietary habits, preferences, and more. 💡 This approach supports both traditional machine learning and generative AI, allowing for more informed and relevant user experiences. 🔍 The system features three memory...
Source: DoorDash Engineering
Raghav Saboo
2026-06-08 19:34
🚀 DoorDash has launched its new Consumer Packaged Goods (CPG) Interest Targeting initiative, enabling advertisers to connect with consumers based on their restaurant order history. This initiative addresses two key questions: which consumer segments to target and how to adjust selections for various campaign objectives. DoorDash's unique access to data allows for a deeper understanding of consumer preferences. By developing a proprietary brand-dish affinity metric, advertisers can now...
Source: DoorDash Engineering
Max Medina
2026-06-01 15:52
🚀 DoorDash has developed a one-click simulation platform for evaluating support chatbots, enhancing pre-launch testing speed and reliability. This platform allows for realistic, multi-turn customer conversations based on various scenarios. It shifts from manual review to automated regression testing, enabling teams to iterate quickly. With this new approach, validation of chatbot features can happen in minutes rather than hours, leading to a significant reduction in errors....
Source: DoorDash Engineering
Chenran Gong
2026-05-27 15:24
🚀 DoorDash is enhancing user experiences with a new framework that utilizes large language models (LLMs) for personalized content generation. 🔍 This system overcomes traditional bottlenecks by creating unique carousels tailored to individual consumer preferences, rather than relying on fixed selections. 💡 Key elements include a consumer memory block, a multi-stage pipeline for content production, and an evaluation framework to refine recommendations. 📊 This approach aims to provide a...
Source: DoorDash Engineering
Yucong Ji
2026-05-21 18:41
🚚 DoorDash is enhancing its logistics by integrating causal machine learning and joint optimization. Dashers may receive peak pay incentives during busy periods to boost supply. This new system aims to balance delivery assignments and incentive allocation to improve overall service quality. By optimizing for delivery duration rather than static targets, DoorDash addresses inefficiencies in its previous models. #DoorDash #Logistics #MachineLearning #DeliveryService #Innovation
Source: DoorDash Engineering
Wei Feng
2026-05-18 16:15
🚀 DoorDash is navigating the challenges of AI and machine learning with their new clusterless ML feature store. This feature store is essential for managing vast amounts of data, crucial for delivering a seamless experience to over a billion users. It supports high-demand services like the Sibyl Prediction Service, processing around 900,000 evaluations per second. The team is learning valuable lessons about scalability, transitioning from Redis to a hybrid database model to enhance...
Source: DoorDash Engineering
Luigi Tagliamonte
2026-05-14 16:32
🚀 DoorDash explores the evolution of food delivery search with its new natural language search (NLS) system. Traditional keyword matching works when users know what they want, but many search intents are more complex. NLS understands these nuanced requests, translating them into structured queries for better results. To evaluate NLS effectiveness, DoorDash shifted from manual annotations to a calibrated LLM judge, improving evaluation speed and accuracy. This change aims to ensure that...
Source: DoorDash Engineering
Xiaochang Miao
2026-05-11 16:12
🚀 DoorDash has developed an AI code reviewer that engineers actually use. Unlike many AI tools that get ignored, this agent focuses on key changes and provides valuable feedback. In a week, it reviews over 10,000 pull requests across various projects, with a high acceptance rate of comments leading to code changes. The aim is to enhance trust and effectiveness in the review process. The third version of this tool has evolved to balance catching critical issues without overwhelming engineers...
Source: DoorDash Engineering
Adam Yarger
2026-04-28 18:40
🚀 Apple unveiled Swift Testing at WWDC 2024, replacing XCTest with faster test execution—up to 7 times quicker! Swift Testing runs tests in parallel, enhancing efficiency and providing better failure messages to aid debugging. DoorDash faced slow XCTest runs impacting CI pipelines, leading to a strategic migration to Swift Testing. They emphasized local ownership, robust tooling, and reliability checks to ensure smooth transitions. With tools like Cursor and SweetPad, engineers can now easily...
Source: DoorDash Engineering
Matheus Gois
2026-04-15 17:25
🚀 Exciting news from DoorDash! We're rolling out passkeys for a more secure and user-friendly login experience. Passkeys replace traditional passwords, offering faster access without the need to remember usernames. They enhance security by reducing phishing risks and syncing across devices. With support from the FIDO Alliance, passkeys are ready for widespread use. This innovation not only improves user experience but also helps reduce fraud and support costs. #Cybersecurity #Passkeys...
Source: DoorDash Engineering
Ron Waisberg
2026-04-14 20:10
🚀 DoorDash is addressing a long-standing challenge in search and recommendations: the quality of content embedding. The article discusses how large language models (LLMs) are enhancing data quality, which is crucial for personalized search experiences. By generating rich profiles for merchants and items, DoorDash is improving semantic search and recommendations across various categories. This strategy aims to create better content embeddings, making it easier for users to discover new items,...
Source: DoorDash Engineering
Xiaochang Miao
2026-03-19 00:04
🚀 DoorDash is transforming its engineering interview process to better align with real-world software development tasks. The traditional format has focused on algorithm drills in isolated settings, which often do not reflect the collaborative nature of actual engineering work. With advancements in AI, this approach is becoming outdated. DoorDash aims to evaluate practical skills crucial in production, including problem-solving in unfamiliar codebases and effective communication. The new...
Source: DoorDash Engineering
Ivan Rudovol
2026-03-09 16:53
🚀 Fraud detection at DoorDash has evolved to meet the challenge of rapid changes in fraud patterns. By shifting from code-based rules to a real-time rules engine, the team can now respond faster without waiting for deployments. This new approach emphasizes safety, explainability, and testing before rollout, enhancing decision-making during critical moments like checkout. Learn more about this innovative strategy! #FraudPrevention #RealTimeTech #DoorDash #Innovation #TechStrategy
Source: DoorDash Engineering
Fengjiao Jiang
2026-02-11 00:52
🚀 DoorDash recently presented DashCLIP at the International Workshop on Multimodal Generative Search and Recommendation in Korea. This new framework generates semantic embeddings for Consumer Packaged Goods (CPG), improving ranking and retrieval tasks by capturing deeper user intent and product information. DashCLIP utilizes multimodal encodings and aligns query embeddings to enhance personalized ad experiences. It incorporates continual pretraining and a curated relevance dataset for robust...
Source: DoorDash Engineering
Omkar Gurjar
2026-02-02 23:29
🚀 DoorDash has reimagined its Dasher onboarding experience to support global growth. The previous system was complex, with varying user journeys across regions, leading to increased maintenance challenges. The new unified, modular platform streamlines signups, allowing for rapid international launches and better localization. This update addresses architectural and operational issues, simplifying the onboarding process for Dasher candidates worldwide. 🌍 #DoorDash #Onboarding #GlobalExpansion...
Source: DoorDash Engineering
Saurabh Gupta
2026-01-26 14:52
🚀 Exciting developments at DoorDash Support! To enhance customer and Dasher experience, we're transitioning from traditional decision trees to large language models (LLMs) for issue resolution. LLMs offer more flexibility and human-like interactions but introduce challenges in testing due to their non-deterministic nature. To address this, we've created a simulation and evaluation flywheel. This system includes an offline simulator that mimics real customer interactions, allowing us to test...
Source: DoorDash Engineering
Lewis Warne
2026-01-20 17:34
📱 Mobile app growth can lead to performance issues and user dissatisfaction. At DoorDash, we noticed our app sizes increasing due to rapid development and added features. To tackle this, we identified key contributors like image assets, build optimizations, and unused code. We implemented targeted strategies and automated monitoring to keep our apps efficient and below the critical 200 MB mark. Smaller apps enhance user experience, ensuring quicker downloads and better performance on all...
Source: DoorDash Engineering
Mike Zaslavskiy
2025-12-16 23:28
📈 At the KDD AI Conference in August 2025, we introduced our research on "Causal Machine Learning for Promotions." Our study outlines a two-stage framework to enhance promotion effectiveness. First, we assess individual customer responses to various offers, then optimize promotions within practical business limits. Promotions can boost growth but often lead to inefficiencies, as many discounted orders would happen without incentives. Our approach aims to identify true promotional impacts and...
Source: DoorDash Engineering
Kun Hu
2025-12-03 22:52
🚀 DoorDash's 2025 summer interns are making a significant impact through hands-on projects. One notable development is the transition to the Logistics Console, enhancing ETA reliability during high-stress events. This new tool validates uploads and tracks changes, improving safety and transparency. Additionally, a "storm mode" feature allows for real-time adjustments during demand surges, streamlining operations and enhancing customer experience. #DoorDash #Internship #SoftwareEngineering...
Source: DoorDash Engineering
Zijian Wei
2025-12-03 22:42
🚀 DoorDash's paper at RecSys 2025 discusses bridging behavioral silos in multi-vertical recommendations using large language models (LLMs). As DoorDash expands, many customers show strong preferences in only a few categories. This leads to challenges in personalizing recommendations across diverse offerings. The proposed LLM framework captures user behavior patterns, allowing for better relevance and personalization, even from the start. It translates varied activity data into meaningful user...
Source: DoorDash Engineering
Nimesh Sinha
2025-12-02 17:43
🚀 Exciting updates from DoorDash! We've launched a GenAI-powered personalized carousel system on our homepage, enhancing your shopping experience. This system tailors recommendations using large language models, creating unique carousels for each user based on their preferences. By analyzing customer data, we're reducing search challenges and helping you make quicker, informed decisions. This means more relevant options and a smoother journey on our platform! #DoorDash #GenAI #Personalization...
Source: DoorDash Engineering
Yuxiang Wang
2025-11-11 21:23
🚀 DoorDash is advancing its AI capabilities by creating a collaborative ecosystem that integrates vast knowledge sources, including experimentation platforms and team chats. This initiative aims to streamline complex business processes that traditionally required multiple tools and steps. The focus is on developing an agentic AI platform for seamless interactions between specialized AI agents. 🤖 Through an evolutionary approach, DoorDash is enhancing multi-agent systems, starting from basic...
Source: DoorDash Engineering
Aydar Akhmetzyanov
2025-11-04 18:13
In early 2024, DoorDash tackled challenges with its in-house search engine to meet global search demands. They achieved a 50% reduction in latency and a 75% decrease in hardware costs. However, they encountered issues with CPU utilization and latency spikes. By transitioning to a new garbage collector and upgrading Apache Lucene, they reduced hardware costs by an additional 30% and improved latency by up to 30%. This experience illustrates how focused optimizations can enhance overall...
Source: DoorDash Engineering
Omik Mahajan
2025-10-30 16:43
🚀 DoorDash introduces SafeChat, an AI-driven feature aimed at enhancing safety for users. The system moderates millions of messages daily, identifying and managing inappropriate content between Dashers and customers. SafeChat employs a three-layered AI approach to ensure effective content moderation, allowing immediate actions when necessary. Learn more about how DoorDash is prioritizing safety on its platform! 🔒📱 #DoorDash #AI #SafetyFirst #TechInnovation #SafeChat
Source: DoorDash Engineering
Bruna Pereira
2025-10-23 17:55
🚀 DoorDash recently presented at KDD 2025's PARIS Workshop, discussing their LLM-assisted personalization framework for multi-vertical retail. The framework focuses on three key dimensions: 1. **Familiarity** - highlighting trusted favorites. 2. **Affordability** - aligning with price preferences. 3. **Novelty** - introducing new and exciting products. This approach aims to enhance customer discovery, ensuring shopping feels personalized and effortless. #DoorDash #Personalization...
Source: DoorDash Engineering
Raghav Saboo
2025-10-20 16:30
DoorDash faced challenges with lengthy CI pipeline durations as web projects grew in complexity. By optimizing tooling and adopting a new monorepo system, they reduced build and test times by 75%, saving over 500 engineering hours monthly. Key strategies included leveraging cobuilds and enhancing parallelization techniques. These changes have significantly improved developer productivity. 🚀💻 #DoorDash #WebDevelopment #ContinuousIntegration #EngineeringEfficiency #TechInnovation
Source: DoorDash Engineering
Aramis Sennyey
2025-10-14 00:37
🚀 Exciting updates from DoorDash's software engineering internship program! This summer, interns contributed to impactful projects including a user-generated content feedback loop. This system notifies users when their reviews gain visibility, fostering engagement and community trust. The project emphasizes the significance of user feedback and includes a streamlined database design for tracking and notifications. Stay tuned for more highlights from our Summer 2025 interns! #DoorDash...
Source: DoorDash Engineering
Cassidy Xu
2025-10-09 16:29
Join us on November 6th in San Francisco for an exclusive event with DoorDash marketing leaders! 🚀 Hear from Gina Igwe, Jennifer Richardi, and Shannon Duncan about how AI is transforming creative marketing. This is a great opportunity to learn, network, and enjoy dinner and drinks. Don't miss out! RSVP by 10/22. #DoorDash #MarketingInnovation #AI #Networking #CreativeLeadership
Source: DoorDash Engineering
Raj Prashad
2025-10-09 12:14
At DoorDash, we embrace AI as a tool to enhance the interview process, not to replace authenticity. Candidates are encouraged to use AI for preparation, like building resumes or exploring interview questions, but must showcase their true selves during interviews. Remember, honesty is key! Misrepresenting your skills could lead to disqualification. For any accommodations regarding AI use, communicate with your recruiter early on. #DoorDash #AIInInterviews #JobPreparation #Authenticity...
Source: DoorDash Engineering
Raj Prashad
2025-09-30 13:03
🚚 Autonomy is advancing rapidly, with autonomous vehicles becoming more common in cities. However, local delivery presents unique challenges. The "last ten feet" problem complicates food and grocery delivery, requiring nimble vehicles to navigate sidewalks and driveways efficiently. Local delivery also involves coordinating busy merchants, diverse consumer preferences, and dynamic marketplace conditions. DoorDash's new Dot robot aims to address these challenges, optimizing local commerce and...
Source: DoorDash Engineering
Stanley Tang
2025-09-29 16:07
🚀 DoorDash is enhancing grocery delivery by leveraging restaurant order histories to recommend items. By using large language models (LLMs), they analyze consumer preferences to provide personalized grocery suggestions. This approach addresses the "cold start problem" for new customers in grocery shopping. The system translates order history into relevant grocery recommendations, making it easier for users to find items they love. For more details, check out the article! 📦🍜🥡 #DoorDash...
Source: DoorDash Engineering
Yucong Ji
2025-09-23 18:03
🚀 DoorDash Ads is enhancing consumer experience by implementing a budget A/B framework for ad testing. This innovative approach helps maintain low delivery fees while ensuring relevant ads. The framework addresses challenges in a three-sided marketplace, where classic A/B tests often fall short due to issues like cannibalization and network effects. By creating separate budget pools, DoorDash can achieve unbiased results. Learn more about how this strategy supports consumers, restaurants, and...
Source: DoorDash Engineering
Nikhil Thomas Joy
2025-09-22 20:41
🚀 Exciting updates from DoorDash's software engineering internship! This summer, interns contributed to meaningful projects, including enhancing the Merchant Support Hub. Key improvements were made to streamline communication for merchants, addressing issues like visibility and fragmented support interactions. The new features in Support Hub v1.5 include accessing email content, unread indicators, and the ability to reply directly to support agents. These enhancements aim to boost merchant...
Source: DoorDash Engineering
Pascal Bell
2025-09-15 18:57
🚨 DoorDash has developed an anomaly detection platform aimed at identifying fraud trends earlier. The system scans millions of user segments to detect subtle behavioral changes that may indicate emerging fraud patterns. Key concepts include anomalous trend detection, focusing on collective user behavior, and anomalous outlier detection, which identifies individual anomalies. This proactive approach seeks to mitigate potential losses before they escalate. #FraudDetection #DoorDash...
Source: DoorDash Engineering
Dave Press
2025-09-08 20:04
🚀 This summer, DoorDash participated in the Disability:IN Conference for the first time, joining advocates and leaders focused on disability inclusion in the workplace. Our Able@ DoorDash group led the effort, with speakers Kinzie Keller and Lyndsey Leask sharing valuable insights on neurodiversity and creating accessible environments. We are committed to building inclusive products and practices, and this event provided us with new ideas to enhance our accessibility journey. Learn more about...
Source: DoorDash Engineering
Raj Prashad
2025-09-05 20:37
🚀 Exciting updates from DoorDash's Summer 2025 internship program! Interns are actively involved in impactful projects, enhancing tools for Dashers, merchants, and consumers. One key project focuses on automating the review of never-delivered orders using an in-house language model, improving efficiency and accuracy. This initiative reduces manual workload while addressing data imbalance in ND cases, ensuring better resolution rates. Stay tuned for more insights from our innovative interns!...
Source: DoorDash Engineering
Anning Li
2025-08-18 21:49
DoorDash's support chatbot efficiently addresses numerous questions from Dashers and customers daily. As their marketplace grows, so does the complexity of inquiries. To enhance chatbot knowledge, DoorDash employs large language models (LLMs) paired with clustering algorithms. This method identifies content gaps and drafts articles quickly, streamlining the knowledge base update process. By analyzing escalated chat transcripts, they pinpoint areas needing improvement. This data-driven...
Source: DoorDash Engineering
Tony Luo