Staff Machine Learning Engineer, Traffic Intelligence

This is a fully remote position, open to applicants in United States.

📋 Description

• Take charge of the entire lifecycle of traffic-scoring models, from defining the problem to real-time deployment, while managing adversarial feedback loops and aiming to reduce bot-incident mean time to mitigate (MTTM).

• Design and implement offline-to-online pipelines that generate certified source-of-truth datasets and comprehensive evaluation frameworks.

• Enhance models to operate within stringent millisecond latency requirements at the internet edge, balancing inference costs with incremental value.

• Collaborate with security analysts, data platform engineers, and global infrastructure partners to embed scoring intelligence into automated mitigation processes.

• Act as the machine learning expert for the team, effectively communicating model trade-offs to leadership and cross-functional teams.

• Design and sustain Airbnb’s end-to-end machine learning systems for traffic classification, handling billions of requests daily.

⛳️ Requirements

• Over 9 years of hands-on experience in production machine learning, particularly in non-stationary, adversarial environments such as traffic integrity, bot mitigation, or fraud detection.

• Proven experience in architecting scalable offline-to-online data pipelines suitable for low-latency inference systems.

• A solid understanding of model evaluation metrics, including ROC/AUC, precision/recall, and calibration techniques.

• Experience with large-scale data engineering, warehouse-scale SQL, and feature engineering for high-velocity event streams.

• Practical knowledge of internet edge infrastructure, including CDN/load balancer functionality and HTTP/TLS signatures.

• Experience in cross-functional leadership and mentoring junior engineers.

• MS/PhD in a quantitative discipline or equivalent extensive engineering experience.

• Preferred: PhD in Statistics, Mathematics, Machine Learning, or a closely related quantitative field.

• Preferred: Expertise in advanced graph-based coordination or Sybil network detection.

• Preferred: Familiarity with causal or econometric methods for assessing the business impact of false positives.

• Preferred: Knowledge of Bayesian calibration techniques for adversarially biased, sparse, or imbalanced datasets.

• Preferred: Experience in data governance and platform engineering.

• Preferred: Exposure to LLM agent tooling and benchmarking.

• Must reside in a state where Airbnb, Inc. maintains a registered entity.

🏝️ Benefits

• Eligibility for bonuses.

• Eligibility for equity.

• Comprehensive benefits package.

• Employee travel credits.

• Opportunity for occasional work at an Airbnb office or participation in offsite events, as coordinated with your manager.

• Disability-inclusive application and interview processes with reasonable accommodations available.