Data Engineer, Real Estate Intelligence

Company DescriptionFlipOps is an advanced, all-in-one platform designed to simplify real estate investment processes by replacing multiple tools with a single system. Specializing in distressed property evaluation, FlipOps identifies high-potential opportunities, scores seller motivation, and streamlines deals from discovery to closure. Leveraging cutting-edge technology, including machine learning models, the platform helps real estate wholesalers, flippers, and buy-and-hold investors predict deal outcomes efficiently. Our goal is to empower investors to focus on closing more deals and analyzing less. FlipOps is tailored for professionals seeking innovative and reliable automation in real estate intelligence.Role DescriptionThe Data Engineer will build and maintain the data infrastructure that powers FlipOps' core intelligence features, including distress scoring, lead prioritization, property valuation models, and skip tracing integrations. This role requires experience working with large-scale property datasets and an understanding of how real estate investors use data to identify opportunities, analyze deals, and make acquisition decisions.QualificationsExperience in Data Engineering and building scalable data infrastructureProficiency in Data Modeling and creating well-structured data for analyticsStrong knowledge of Extract, Transform, Load (ETL) pipelines and processesExpertise in Data Warehousing and methods for efficient data storage and retrievalFamiliarity with Data Analytics tools and practices to generate insightsSolid programming skills in languages such as Python, SQL, or similarAbility to work independently and contribute in a remote environment with cross-functional teamsExperience with cloud platforms and real estate-related data is a plusBachelor’s degree in Computer Science, Data Science, or a related field, or equivalent professional experienceWhat You'll DoDesign and maintain ETL pipelines that ingest property records, tax data, lien filings, pre-foreclosure notices, probate records, and MLS data from multiple sourcesBuild and optimize the data models that power FlipOps' distress scoring algorithm, ensuring accuracy across different property types, markets, and distress indicatorsIntegrate third-party skip tracing APIs and develop quality scoring for returned contact data, measuring hit rates by list type and data providerDevelop the data architecture for comp analysis tools, normalizing property attributes like square footage, lot size, condition, and renovation scope across inconsistent data sourcesBuild pipelines that surface motivated seller signals in near-real-time: new liens filed, missed tax payments, code violations, ownership changes, and pre-foreclosure activityCreate and maintain the datasets used by machine learning models for lead scoring, deal outcome prediction, and ARV estimationMonitor data quality and freshness across all property data sources, flagging when a provider's accuracy drops or coverage gaps appear in specific marketsCollaborate with the product team to expose data insights within the investor-facing platform, including pipeline analytics, lead source performance, and conversion metricsYou Might Be a Fit IfYou've built ETL pipelines that process property or real estate data at scale and understand the inconsistencies that come with county-level records, MLS feeds, and third-party aggregatorsYou're proficient in Python, SQL, and at least one modern data orchestration tool like Airflow, Dagster, or PrefectYou've worked with property data APIs or providers like ATTOM, CoreLogic, PropStream, or BatchLeads and know where the data is reliable and where it requires significant cleaningYou have experience building or supporting machine learning models in production, particularly around scoring, classification, or prediction tasksYou've designed data warehouses or lakehouses using tools like Snowflake, BigQuery, Redshift, or Databricks and can make architecture decisions based on query patterns and data volumeYou understand what ARV, MAO, equity position, and distress indicators mean in the context of real estate investing, or you're prepared to learn quicklyYou've dealt with data deduplication challenges — matching property records across sources where addresses are formatted differently, owner names are inconsistent, and parcel numbers don't always alignYou care about data freshness and have built monitoring systems that alert when pipeline latency or source accuracy degradesBonus PointsDirect experience in the real estate or proptech space, working with investor-facing data productsFamiliarity with skip tracing data pipelines and the challenge of maintaining high contact rates as phone numbers and addresses go staleExperience with geospatial data processing — driving for dollars route optimization, property clustering by neighborhood, or market heat mappingBackground in building recommendation or ranking systems, particularly for surfacing high-priority items from large candidate poolsYou've worked with DNC/TCPA compliance datasets and understand how to integrate regulatory data into outreach toolingCompensation$78,000-$85,000. Remote-friendly.