Key skills
ML model productionalizationDistributed systemsData processing frameworksETL pipelinesFeature engineeringTeam leadershipCommunication skillsProblem solvingMachine LearningMLETLData EngineeringAnalyticsSparkCommunication
About this role
Airbnb is a global company that has transformed the way people travel by connecting hosts and guests. They are seeking a Staff Software Engineer to develop advanced tools for hosts, focusing on machine learning model predictions and personalized user experiences, while collaborating with cross-functional teams to enhance the performance of their systems.
Responsibilities:
- Design and manage end-to-end data workflows to support the ML engineering lifecycle, focusing on preparing data for model training, tracking data lineage, evolving schemas to adapt to changing needs, and ensuring data integrity and reliability in production
- Prototype new ideas and influence the serving strategy
- Build and optimize real-time serving systems to deliver low-latency, high-throughput APIs for model predictions and personalized recommendations, ensuring reliable and scalable performance in production environments
- Collaborate with other product engineers and cross-functional partners to develop new Host pricing functionality and surface model recommendations, insights and analytics
- Contribute to the development of long-term workflow strategies, roadmaps and ML serving development within the Host Pricing organization
- Mentor and coach team members, providing guidance in ML serving and data engineering best practices and support to enhance their skills and performance
Requirements:
- 9+ years of experience with a BS/Masters or 4+ years with a PhD
- Experience leading teams, setting technical direction, building & launching high-impact models
- Experience influencing partners as well as other engineering teams
- Strong ownership and experience building and operating high-scale, distributed systems across the full software life cycle
- Excellent communication skills and the ability to work well within a team and across engineering teams
- Expertise in large-scale distributed data processing frameworks like Presto or Spark
- Prior experience with the whole lifecycle of productionalization of ML models, including ETL pipelines for data training, feature generation, model evaluation and real-time serving
- Strong problem solver and solid production debugging skills