Staff Machine Learning Engineer, Traffic Intelligence
Airbnb · United States
About this role
**Airbnb — Staff Machine Learning Engineer, Traffic Intelligence** **About the team** Airbnb’s web and API surfaces handle requests from guests and hosts alongside a growing volume of automated agents (AI assistants, crawlers, and scrapers). The team builds systems that bring clarity to this traffic by combining in-house ML with vendor signals to decide in real time how to serve billions of daily requests. Anti-bot and anti-scraping detection is a key mandate, with the broader goal of full traffic classification—building evaluation frameworks that distinguish legitimate automation from abusive actors across the fleet. **The impact you’ll make** - Architect and maintain end-to-end traffic classification ML systems, balancing high-performance model deployment with rigorous offline data pipelines. - Harden edge-traffic policies to reduce bot-incident MTTM. - Establish rigorous evaluation practices to ensure foundational signal accuracy and evasion-resistance across the fleet. **A typical day** - Own the full lifecycle of traffic-scoring models—from problem framing to real-time deployment—managing the adversarial feedback loop to improve evasion-resistance and reduce bot-incident MTTM. - Build robust offline-to-online pipelines that produce certified source-of-truth datasets, including stratified benchmarks and leakage-prevention checks. - Optimize models within strict millisecond latency budgets at the internet edge, balancing inference costs with incremental value and maintaining fleet-wide fail-open behaviors. - Partner daily with security analysts, data platform engineers, and international infrastructure partners to integrate scoring intelligence into automated mitigation workflows and ensure global consistency despite regional failovers or CDN updates. - Serve as the team’s ML authority, communicating model trade-offs to leadership and cross-functional teams and translating research into scalable engineering guidance. **Your expertise** - 9+ years of applied production ML experience in non-stationary, adversarial domains (e.g., traffic integrity, bot mitigation, or fraud), including managing feedback loops against adaptive actors. - Experience architecting scalable offline-to-online data pipelines that produce certified source-of-truth datasets for low-latency inference. - Strong model evaluation skills (e.g., ROC/AUC, precision/recall, calibration) and ability to communicate trade-offs. - Large-scale data engineering experience (warehouse-scale SQL) and feature engineering on high-volume event streams. - Practical knowledge of internet edge infrastructure (e.g., CDN/load balancer behavior, HTTP/TLS signatures) and how it relates to foundational signal verification. - Cross-functional leadership experience, including mentoring and driving initiatives through shared datasets and consumer contracts. - MS/PhD in a quantitative field (e.g., Statistics, ML) or equivalent deep engineering experience, with significant ownership of large-scale systems measuring evasion-resistance. **Preferred** - PhD in Statistics, Mathematics, Machine Learning, or related quantitative discipline. - Advanced expertise in graph-based coordination or Sybil network detection. - Causal/econometric methods to model business impact of false positives on legitimate traffic. - Bayesian calibration techniques for adversarially-biased, sparse, or imbalanced datasets. - Data governance and platform engineering experience managing certified dataset lifecycles and do
Listing freshness
CronJobs last confirmed this listing 19h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.