Senior Data Scientist, Algorithms - Identity (Trust)

Airbnb

2h•Remote

About The Position

Airbnb was born in 2007 when two hosts welcomed three guests to their San Francisco home, and has since grown to over 5 million hosts who have welcomed over 2 billion guest arrivals in almost every country across the globe. Every day, hosts offer unique stays and experiences that make it possible for guests to connect with communities in a more authentic way. The Community You Will Join: “Our real innovation is not allowing people to book a home; it’s designing a framework to allow millions of people to trust one another. Trust is the real energy source that drives Airbnb…” - Brian Chesky, Airbnb Co-Founder & CEO (2019) Trust is essential for building a vibrant Airbnb community. The Identity Data Science team aims to help create the most trusted community in the world by ensuring that all Airbnb users are who they say they are. We work closely with product, engineering, and operations teams to build cutting-edge identity verification systems and implement effective defenses against emerging threats. The Difference You Will Make: This role is unique because it provides opportunities to improve the social well-being of real-world users by ideating novel algorithmic and data-driven solutions. The ideal candidate will be a motivated and talented “Full-Stack” Data Scientist with a broad methodological toolkit, who can own and drive forward challenging and high-visibility initiatives like: Improve on industry standards in identity verification by leveraging biometrics, NFC chips, Apple/Google integrations, and other advancements in identity verification technologies Build high-performing statistical models for detecting identity fraud, such as computer vision models for identifying fake or tampered images, LLMs for surfacing suspicious user account attributes, or graph-based models for uncovering hidden clusters of bad actors Automate and optimize human-in-the-loop ML processes for classifying fraud and generating other labels of interest for model training and evaluation Deploy a real-time anomaly detection system for quickly identifying emerging threats across regions, cohorts, and platforms Design intelligent sampling jobs for estimating rare events prevalence and other hard-to-measure metrics like recall and false positive/negative rates

Requirements

5+ years of industry experience in a quantitative analysis role with a Master’s degree in a quantitative field (computer science, statistics, economics, etc.), or 2+ years of experience with a Ph.D.
State-of-the-art knowledge of AI/ML models
Strong knowledge of causal inference
Skilled in statistical programming (Python or R) and database usage (SQL)
Proven ability to communicate clearly and effectively to audiences of varying technical levels
Ability to translate complex findings and results into compelling narratives that drive impact
Excellent project management, communication, and collaboration skills

Nice To Haves

Trust & Safety experience is a plus

Responsibilities

Build and deploy production AI/ML models for detecting identity fraud and improving Airbnb’s identity verification systems (feature engineering, model development + evaluation, threshold selection, error analysis, model lifecycle management)
Conduct experiments and lead quantitative analyses for measuring impact, surfacing critical gaps, and identifying opportunities for improvement
Develop methodologies and frameworks for analyzing the tradeoffs associated with new interventions and propose strategies for optimizing impact
Deliver robust research reports with effective data visualizations, clear storytelling, and bullet-proof accuracy to drive forward impact in collaboration with cross-functional partners in product, engineering, and operations
Think strategically about opportunities to improve and scale our identity verification processes and defenses