Join us on Wednesday, July 23rd, at 4:00 PM for a tech talk with AI & ML leaders at Airbnb. A light happy hour will follow for in-person attendees with Airbnb Tech Leadership. Limited in-person seats available on a first come, first serve basis by RSVP.
A confirmation email with additional event information will be emailed to attendees prior to the event.
In a world of infinite choices, Airbnb is reimagining how personalized discovery works at global scale. This talk explores how ranking, recommendations, retrieval, and GenAI come together across Airbnb’s platform to guide guests and hosts through diverse, dynamic journeys. From large-scale learning-to-rank systems and embedding-based search to contextual bandits, generative metadata, and agentic AI, we’ll share how intelligence is woven into every touchpoint—along with a look at what’s next in adaptive, modular AI for discovery.
Airbnb’s mission is to deliver effortless, world-class support for every guest and host. This talk unpacks the Airbnb AI Assistant that makes that possible—an end-to-end system that fuses rich and high quality data, robust evaluation platform, models, and guardrails. We’ll discuss how these components are designed to interact with the goal of delivering responses that are fast, accurate, and aligned with applicable policies, while incorporating feedback to support ongoing improvement. Attendees will gain insights into approaches and considerations for designing, deploying, and scaling robust AI assistants intended for community support.
Chronon, Airbnb's innovative declare feature platform, is designed to address the unique challenges faced by AI/ML practitioners.
In this talk, learn about Chronon's architecture that guarantees online-offline consistency through a shared computation engine. This session covers high throughput low-latency feature serving, Python API functionality, feature derivation capabilities, and recent enhancements. We'll also explore future roadmap items including potential integration with unstructured data.
Sanjeev Katariya is a veteran technology executive, inventor, and thought leader in artificial intelligence and machine learning with over 33 years of experience in the tech industry, including 22+ years in executive leadership roles. He currently serves as the Head of Relevance and Personalization at Airbnb, where he leads core initiatives in large-scale AI/ML discovery systems, generative AI, and personalized recommendation and search technologies. Sanjeev holds over 40 patents and has authored multiple influential publications in areas such as reinforcement learning, multi-objective ranking, and intelligent system architecture. His innovations span leadership tenures at Microsoft, eBay, InVision, LinkedIn, and Airbnb, and he brings extensive hands-on AI experience from working with startups and academic research programs, contributing to production-scale systems used by millions. He currently serves on the Board of Directors at Grand Valley State University (GVSU) and previously advised the AI Research Institute in Dearborn, underscoring his commitment to bridging industry and academia.A passionate advocate for education and responsible AI, he has also curated projects like the “AI/DS/ML Map of Everything”—a comprehensive, visual encyclopedia of modern AI and machine learning.
Yashar Mehdad is a Principal AI Engineer at Airbnb, where he architects and scales generative-AI solutions that power community support and other experiences for millions of guests and hosts. Before Airbnb, he led the rollout of conversational AI across WhatsApp, Messenger, and Instagram within Meta’s Generative AI organization, bringing large-language-model capabilities to some of the world’s largest messaging platforms. He has also driven ML and NLP products for global enterprises such as Yahoo and several startups, effectively bridging research and industry. Earlier in his career, Yashar conducted research in natural language processing as a part of his academic career, laying the foundation for his applied work. With more than 15 years of turning state-of-the-art ML and AI technologies into production systems, he has published widely at top-tier venues on conversational AI, summarization, language generation, abusive- and risky-content detection, as well as multilingual and multimodal systems. Yashar remains an active member of the NLP community, frequently serving as a program-committee member and workshop co-chair at leading conferences
Pengyu is a software engineer specializing in artificial intelligence and machine learning infrastructure, with particular expertise in feature platforms at Airbnb. With over ten years of industry experience, he recently led the open-sourcing of Chronon (formerly known as Zipline), Airbnb's machine learning feature platform.
Driven by a passion for open source projects and community development, Pengyu's work focuses on creating robust infrastructure to power AI/ML applications at scale. Prior to joining Airbnb, he contributed to data platform development and AI/ML-driven product teams at Capital One.
Carolina Barcenas is a seasoned Data Science leader with extensive experience in the technology and finance sectors. Currently serving as the Head of Platform Data Science at Airbnb since May 2022, Carolina previously held multiple senior roles at Visa from March 2015 to September 2022, including SVP of Visa Research, where significant advancements in artificial intelligence, blockchain, and security were made. Carolina transformed the research organization into an innovation powerhouse and pioneered a rapid prototyping tool that significantly reduced development time. Prior to Visa, Carolina contributed to PayPal's risk management and worked at Austin Logistics on machine learning models for top financial institutions. With academic credentials including a PhD and MS from Georgia Institute of Technology, along with degrees from Tecnológico de Monterrey, Carolina possesses a robust foundation in operations research, statistics, and engineering.
