Staff Machine Learning Engineer, Traffic Intelligence

What you'll do

• Manage the full lifecycle of traffic-scoring models from initial problem framing to real-time deployment.
• Architect offline-to-online data pipelines to produce certified source-of-truth datasets for model evaluation.
• Optimize machine learning models to meet strict millisecond latency budgets at the internet edge.
• Develop rigorous evaluation frameworks to ensure model accuracy and resistance against adversarial actors.
• Integrate scoring intelligence into automated mitigation workflows in coordination with security and infrastructure teams.
• Serve as a technical authority by communicating complex model trade-offs to leadership and cross-functional partners.
• Engineer features from high-volume event streams to build reliable, production-ready modeling pipelines.

What we're looking for

• 9+ years of experience in production ML within non-stationary, adversarial domains like traffic integrity or fraud.
• Experience architecting scalable offline-to-online data pipelines for low-latency inference systems.
• Strong foundation in rigorous model evaluation metrics such as ROC/AUC, precision/recall, and calibration.
• Experience with large-scale data engineering using warehouse-scale SQL and feature engineering on high-volume event streams.
• Practical knowledge of internet edge infrastructure including CDN, load balancer behavior, and HTTP/TLS signatures.
• Proven track record of cross-functional leadership and mentoring junior engineers on technical quality.
• MS or PhD in a quantitative field like Statistics or Machine Learning, or equivalent deep engineering experience.
• Advanced expertise in graph-based coordination, Sybil detection, causal methods, or Bayesian calibration (preferred).