Airbnb Engineering

@AirbnbEng

Creative engineers building a world where you can belong anywhere.

San Francisco, CA

airbnb.io

Joined September 2012

Airbnb Engineering
@AirbnbEng
Aug 20
Stale assumptions. Ghosts from COVID. Models still forecasting a world that no longer exists. A good forecasting team doesn't just learn from shocks, it learns to forget them, on purpose. Here's how we built the discipline to know when.
How we knew COVID was over (and what our models had to unlearn)
From medium.com
Airbnb Engineering
@AirbnbEng
Aug 17
What happens when a login screen doesn't know which challenge a user can actually complete? We rebuilt authentication from the ground up and the results speak for themselves.
Flexible Authentication: Reimagining authentication for millions of users at Airbnb
From medium.com
Airbnb Engineering
@AirbnbEng
Aug 10
False confidence. Undetected regressions. Wasted effort. These are what happen when GenAI teams skip rigorous evaluation. We've been there. Here's how we team built eval-driven development to ship trustworthy AI products.
Eval-driven development: Lessons from evaluating GenAI at scale
From medium.com
Airbnb Engineering
@AirbnbEng
Jul 27
97.8% of guest activity is just listing views. We built a sequence model that learns from that noise plus years of booking history — and made search meaningfully more personalized.
Personalizing Airbnb search by learning from the guest journey
From medium.com
Airbnb Engineering
@AirbnbEng
Jul 23
Training an LLM is the easy part. Trusting your evaluation of it is hard. We rebuilt our eval infra around deterministic evaluation to minimize confounders + "micro adapters" for targeted fixes & went from weeks long iteration loops to same day fixes.
From weeks to a day: how we made LLM evaluation fast enough to iterate on
From medium.com