The opportunity
Airbnb was born in 2007 when two hosts welcomed three guests to their San Francisco home, and has since grown to over 5 million hosts who have welcomed over 2 billion guest arrivals in almost every country across the globe. Every day, hosts offer unique stays and experiences…
What you'll do
Define the architecture and contracts governing how models move from: development to production — feature store design, model schema management, online/offline inference consistency, and multi-version support.
Lead the buildout of a unified serving stack that eliminates per-model: one-off implementations and gives data scientists a turnkey path from training to production.
Architect backfill and evaluation infrastructure so the modeling team can: simulate production inference over historical data in days, not weeks.
Establish domain contracts between Modeling and Serving so each team can move: independently with clear, enforced interfaces.
Review and evolve the ML serving architecture: making tradeoff calls on feature pipeline design, model composition, and API interfaces.
Write and review code for feature engineering jobs, feature store: configurations, and serving service endpoints.
What they're looking for
- Partner with Data Science, MLE, MLI and core Pricing & Availability systems: BE teams to define artifact handoffs and integration contracts.
- Drive milestone planning across the Host Pricing & Settings org, sequencing: work to deliver value incrementally.
- Mentor engineers through design reviews and hands-on pairing on the hardest infrastructure problems.
- + years in backend or platform engineering, with substantial experience: building production ML systems or data-intensive infrastructure.
