Senior Software Engineer, Assistant Engineering
Core
Design and build scalable data systems, evaluation platforms, and observability tools for Airbnb's agentic AI products to measure, monitor, and improve AI quality.
Role type
Senior Software Engineer (Backend/Data Systems for AI Evaluation)
Builds
Scalable data pipelines, evaluation frameworks, and observability tools for agentic AI products
Domain
AI/ML Product Evaluation, Big Data Systems, Backend Engineering
Deliverable
production ML models | infrastructure
Required skills
Python, scalable data pipeline design, data modeling, system design, cross-functional collaboration
Preferred skills
Airflow, Spark, Flink, Kafka, Trino/Presto, Hive, Iceberg, LLM-as-a-judge, AI/ML system concepts
Technologies
Python, Airflow, Spark, Flink, Kafka, Trino/Presto, Hive, Iceberg
Responsibilities
Design and productionize scalable data systems for AI evaluation and metric computation; Build data models and processing pipelines for agentic AI interactions; Develop LLM-as-a-judge solutions and data pipelines to address metric challenges; Collaborate with ML infrastructure teams to evolve evaluation frameworks; Lead software development lifecycle including architecture, implementation, and testing.
Seniority
Senior, hands-on IC