All interviews

Airbnb

Senior

Build end-to-end search ranking and personalization ML systems across Airbnb's platform

Airbnb's Relevance and Personalization team owns search and recommendation ranking across the entire platform, spanning data pipelines, feature/model innovation, and serving/experimentation infrastructure at scale. This interview tests hands-on ML engineering depth — productionizing models (batch and real-time), ML best practices like training/serving skew and feature selection, and fluency with tools like TensorFlow, PyTorch, Kubernetes, Spark, or Kafka. Strong candidates show they can both build models and reason about the surrounding infrastructure (feature platforms, model interpretability, hyperparameter optimization, concept drift).

Step into this interview

Free · a live voice mock calibrated to this exact role

Practice this interview

What this interview tests

  • Productionizing ML models for batch and real-time ranking/personalization
  • ML best practices: training/serving skew, feature/model selection, A/B testing
  • Search ranking and recommendation systems at scale
  • ML infrastructure: feature platforms, model interpretability, concept drift detection
  • Cross-functional collaboration with PMs, engineers, and data scientists

Common question themes

Walk through a ranking or personalization model you took from prototype to production

How do you detect and mitigate training/serving skew

Describe incorporating a new signal type (image, text, sequential) into a ranking model

How would you design an A/B test for a ranking algorithm change in a two-sided marketplace

Tell me about building or improving ML infrastructure like a feature platform or drift detection

View the original posting