3 months ago
Base Salary
$212k - $265k/yr
Responsibilities
- Own the complete lifecycle of traffic-scoring models from problem framing through real-time deployment, including adversarial feedback loops and evasion resistance.
- Architect offline-to-online pipelines and certified source-of-truth datasets with rigorous evaluation frameworks, stratified benchmarks, and leakage-prevention checks.
- Optimize model inference within strict millisecond latency budgets at the internet edge while balancing cost and incremental value and maintaining fail-open behavior.
- Partner with security analysts, data platform engineers, and international infrastructure teams to integrate scoring intelligence into automated mitigation workflows.
- Serve as the team’s machine learning authority by communicating model trade-offs to leadership and cross-functional stakeholders.
- Mentor junior engineers and provide scalable engineering guidance on technical quality and system design.
Requirements
- 9+ years of applied production ML experience, specifically in non-stationary and adversarial domains such as traffic integrity, bot mitigation, or fraud.
- Experience architecting scalable offline-to-online data pipelines and certified source-of-truth datasets for low-latency inference systems.
- Strong knowledge of model evaluation, including ROC/AUC, precision/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 and experience mentoring junior engineers on technical quality and design practices.
- MS or PhD in a quantitative field such as Statistics or Machine Learning, or equivalent deep engineering experience.
- Preferred: PhD in Statistics, Mathematics, Machine Learning, or a related quantitative discipline.
- Preferred: advanced expertise in graph-based coordination or Sybil network detection methods.
- Preferred: experience with causal or econometric methods for modeling false-positive impact on legitimate traffic.
- Preferred: experience implementing Bayesian calibration for adversarially biased, sparse, or imbalanced datasets.
- Preferred: familiarity with data governance, platform engineering, certified dataset lifecycles, and downstream consumer contracts.
- Preferred: exposure to LLM agent tooling and benchmarking focused on inference cost, latency, and value trade-offs.
Benefits
- US remote eligible, with occasional office or offsite work as agreed with the manager.
- May be eligible for bonus, equity, benefits, and Employee Travel Credits.
Tech Stack
Categories
Data EngineeringML Engineering
About Airbnb
Airbnb operates a global online marketplace that connects hosts offering homes, rooms, and unique properties with travelers seeking short-term stays and experiences. The company earns revenue primarily through service fees on bookings; founded in 2007 and headquartered in San Francisco, it is a public company on NASDAQ (ABNB) with over 5 million hosts and guest arrivals recorded in nearly every country.