Staff Machine Learning Engineer

Key Skills

Apache Airflow, Data Architecture, Data Modeling, Data pipelines, Databricks, Design, Google BigQuery, Machine learning techniques, Python Programming, Snowflake, SPARK Programming

Job Description

About Opendoor

Founded in 2014, Opendoor’s mission is to empower everyone with the freedom to move. We believe the traditional real estate process is broken and our goal is simple: build a digital, end-to-end customer experience that makes buying and selling a home simple, certain and fast. We have assembled a dedicated team with diverse backgrounds to support more than 100,000 homes bought and sold with us and the customers who have selected Opendoor as a trusted partner in handling one of their largest financial transactions. But the work is far from over as we continue to grow in new markets. Transforming the real estate industry takes tenacity and dedication. It takes problem solvers and builders. It takes a tight knit community of teammates doing the best work of their lives, pushing one another to transform a complicated process into a simple one. So where do you fit in? Whether you’re passionate about real estate, people, numbers, words, code, or strategy -- we have a place for you. Real estate is broken. Come help us fix it.

About the Team

The Machine Learning Foundation team owns the frameworks and systems necessary to empower rapid and sustained iteration on Opendoor’s industry-leading models for pricing, risk, and macro forecasting in real estate. The ability to rapidly experiment and deploy models is central to Opendoor’s ability to thrive in a dynamic marketplace. This team will work with MLEs and Researchers to design and support next generation ML infrastructure.

Role Responsibilities:

• Designing, implementing, and supporting a framework for the full ML lifecycle specialized to Opendoor’s unique requirements
• Maintaining and operating critical, large-scale ML pipelines such as Opendoor’s Valuation Model
• Productionizing and modernizing features, pipelines, and their store
• Integrating solutions with industry-standard ML PaaS such as MLFlow, Databricks, Anomalo, and Snowflake

Skills Needed:

• BS or MS degree in Computer Science, Engineering, or a related technical field
• 8+ years of experience working with large-scale data / ML pipelines and their supporting infrastructure
• Proficiency with systems design and data modeling
• Fluency with workflow management tools, like Airflow or dbt
• Experience with modern data warehouses, like Snowflake, Databricks, or BigQuery
• Familiarity with distributed batch compute technologies such as Spark.
• Expertise breaking down complex problems, documenting solutions, and sequencing work to make iterative improvements
• Significant experience with Python
• Familiarity with software design principles, big data architecture, and test-driven development