How we knew COVID was over (and what our models...
When we retrain, when we rebuild, and when we leave a model alone.
Flexible Authentication: Reimagining authentication for millions of users at Airbnb
Rebuilding login and signup surfaced product insights, not just technical challenges. Here’s how we designed Flexible...
Recent Articles
Eval-driven development: Lessons from evaluating GenAI at scale
How Airbnb teams build trustworthy Generative AI products by treating evaluation as a first-class engineering discipline;...
Personalizing Airbnb search by learning from the guest journey
How we built a Transformer-based sequence model that encodes years of guest behavior to surface the...
From weeks to a day: how we made LLM evaluation...
Training an LLM is the easy part. The hard part is designing experiments and evaluations that...
Scaling beyond one: How Airbnb evolved its data architecture for...
How Airbnb’s data engineers and analytics engineers built a consistent and flexible data modeling framework to...
Sitar-agent: Building a reliable dynamic configuration sidecar at scale
How Airbnb built a Kubernetes sidecar to deliver dynamic configuration reliably at scale.
When history fails you, borrow from geography
How Airbnb used sequential geographic recovery signals and prior propagation to generate reliable corridor-level forecasts when...
