Staff Machine Learning Engineer, Traffic Intelligence

Details

Airbnb is building systems that classify web and API traffic from guests, hosts, AI assistants, crawlers, and scrapers. The team combines in-house machine learning and vendor signals to make real-time decisions for billions of daily requests, with a focus on anti-bot, anti-scraping detection, and distinguishing legitimate automation from abusive actors.

Responsibilities

• Own the complete lifecycle of traffic-scoring models, from problem framing through real-time deployment, while managing adversarial feedback loops and improving evasion resistance.
• Architect offline-to-online pipelines that produce certified source-of-truth datasets.
• Establish rigorous evaluation frameworks, including stratified benchmarks and leakage-prevention checks, so model improvements are empirically measurable and defensible.
• Optimize models within strict millisecond latency budgets at the internet edge, balancing inference costs against incremental value and maintaining fleet-wide fail-open behaviors.
• Partner with security analysts, data platform engineers, and international infrastructure partners to integrate scoring intelligence into automated mitigation workflows.
• Ensure global consistency in traffic classification despite regional failovers and CDN updates.
• Serve as the team's machine learning authority by communicating model trade-offs to leadership and cross-functional teams.
• Mentor junior engineers on technical quality and design practices.

Requirements

• 9+ years of applied experience in production machine learning, particularly in non-stationary, adversarial domains such as traffic integrity, bot mitigation, or fraud.
• Experience architecting scalable offline-to-online data pipelines for low-latency inference systems.
• Strong foundation in model evaluation, including ROC/AUC, precision and recall, and calibration.
• Experience with large-scale data engineering, warehouse-scale SQL, and feature engineering on high-volume event streams.
• Practical knowledge of internet edge infrastructure, including CDN and load balancer behavior and HTTP/TLS signatures.
• Proven cross-functional leadership experience, including delivering initiatives through shared datasets and consumer contracts.
• MS or PhD in a quantitative field such as Statistics or Machine Learning, or equivalent deep engineering experience.

Preferred Qualifications

• PhD in Statistics, Mathematics, Machine Learning, or a related quantitative discipline.
• Advanced expertise in graph-based coordination or Sybil network detection methods.
• Experience with causal or econometric methods for modeling the business impact of false positives on legitimate user traffic.
• Experience implementing Bayesian calibration techniques for adversarially biased, sparse, or imbalanced datasets.
• Familiarity with data governance and platform engineering practices for managing certified datasets and downstream consumer contracts.
• Exposure to LLM agent tooling and benchmarking, including inference cost, latency, and value trade-offs.

Work Location

This position is US remote eligible. The role may include occasional work at an Airbnb office or attendance at offsites, as agreed with the manager. Candidates must live in a state where Airbnb, Inc. has a registered entity.

Compensation

The base pay range is $212,000–$265,000 USD. The role may also be eligible for bonus, equity, benefits, and Employee Travel Credits.