Airbnb is a leading platform for unique stays and experiences, and they are seeking a Senior Staff Software Engineer for the Host Pricing & Settings team. This role involves owning the technical strategy for ML serving infrastructure, leading the buildout of a unified serving stack, and mentoring engineers while ensuring seamless integration of data science and engineering efforts.
Responsibilities:
- 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
- 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
Requirements:
- 12+ years in backend or platform engineering, with substantial experience building production ML systems or data-intensive infrastructure
- Strong programming skills in Java, Kotlin, Scala, and/or Python
- Deep understanding of ML systems design: feature stores, training/serving consistency, model versioning, and online/offline inference pipelines
- Experience with high-scale batch and real-time data pipelines (Spark, Airflow, Kafka, or equivalent), including point-in-time correctness for backfills
- Expertise with architectural patterns of large, high-scale applications — well-designed APIs, efficient data contracts, multi-tenant serving infrastructure
- Proven ability to lead cross-team technical initiatives spanning ML and platform engineering
- Production experience with Chronon, Tecton, Feast, or equivalent — including online/offline consistency and backfill automation
- Experience with model schema management, multi-version support, and model composition frameworks
- Track record defining and enforcing technical contracts between ML modeling, MLI, serving teams and/or product surfaces
- Measurable impact improving the speed at which ML teams evaluate candidate models and ship to production