Staff Machine Learning Engineer

Who you are

• 9+ years of applied experience in production ML, specifically within non-stationary, adversarial domains (e.g., traffic integrity, bot mitigation, or fraud) where you have managed the feedback loop against adaptive actors
• Demonstrated experience architecting scalable, offline-to-online data pipelines that produce certified source-of-truth datasets for low-latency inference systems
• Strong foundation in rigorous model evaluation, including metrics like ROC/AUC, precision/recall, and calibration, with an ability to communicate complex trade-offs to cross-functional stakeholders
• Experience with large-scale data engineering (warehouse-scale SQL) and feature engineering on high-volume event streams to build reliable, production-ready modeling pipelines
• Practical knowledge of internet edge infrastructure (e.g., CDN/load balancer behavior, HTTP/TLS signatures) and their role in verifying foundational signals
• Proven track record of cross-functional leadership, landing initiatives through shared datasets and consumer contracts while mentoring junior engineers on technical quality and design practices
• 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
• PhD in Statistics, Mathematics, Machine Learning, or a related quantitative discipline
• Advanced expertise in graph-based coordination or Sybil network detection methods for complex, distributed system analysis
• Deep experience with causal or econometric methods to model the business impact of false positives on legitimate user traffic
• Experience implementing Bayesian calibration techniques for handling adversarially-biased, sparse, or imbalanced datasets
• Familiarity with data governance practices and platform engineering, specifically managing the lifecycle of certified datasets and downstream consumer contracts
• Exposure to LLM agent tooling and benchmarking, with a focus on optimizing inference costs against latency and value trade-offs

What the job involves

• You will architect and maintain Airbnb’s end-to-end traffic classification ML systems, balancing high-performance model deployment with rigorous offline data pipelines
• Success is measured by your ability to harden edge-traffic policies—targeting reduced bot-incident MTTM—and by establishing rigorous evaluation practices that ensure foundational signal accuracy and evasion-resistance across the fleet
• Own the complete lifecycle of traffic-scoring models, from problem framing to real-time deployment, managing the adversarial feedback loop to ensure high evasion-resistance and directly drive reductions in bot-incident MTTM
• Architect robust offline-to-online pipelines that produce certified source-of-truth datasets, establishing rigorous evaluation frameworks—such as stratified benchmarks and leakage-prevention checks—to ensure every model improvement is empirically measurable and defensible
• Execute model optimization within strict millisecond latency budgets at the internet edge, uniquely balancing inference costs against incremental value while 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, ensuring global consistency in traffic classification despite regional failovers or CDN updates
• Serve as the team’s machine learning authority, communicating complex model trade-offs to leadership and cross-functional teams to translate technical research into practical, scalable engineering guidance

Benefits

• Paid volunteer time
• Health food and snacks
• Generous parental and family leave
• Learning and development
• Annual travel and experiences credit