Senior Data Scientist, Research & Applied Science

Faropoint•Hoboken, NJ
•$160,000 - $200,000•Onsite

About The Position

Faropoint is seeking a senior data scientist to own and improve predictive models used to inform real estate investment, leasing, property sales, and tenant credit decisions. The models estimate market rent, forecast lease renewals, price property sales, assess tenant credit risk, and support entity de-duplication. The role requires rigorous judgment in a fragmented market where comparable data is limited. The senior data scientist will explain model methods and results to internal decision-makers and external investors, establish standards for validation and experimentation, collaborate with the Director of Research on research priorities, and mentor junior data scientists. The position is based on site in Hoboken, New Jersey. The data scientist will develop trustworthy, reproducible model research; validate candidate data sources and modeling approaches against real-world outcomes; build backtesting, error analysis, and monitoring; and maintain reliable production inference and model-serving systems on AWS. The role also owns evaluation methodology for LLM-based document extraction and partners with investment, research, and asset-management colleagues to answer business questions and communicate uncertainty. Faropoint owns and operates last-mile, Class B, small-bay industrial properties across more than 20 U.S. markets. Its in-house technology team builds proprietary software and predictive models used by investors and asset managers.

Requirements

  • At least 6 years of applied statistics or machine learning experience, including ownership of production models after launch.
  • Strong Python and SQL skills.
  • Deep experience building predictive models on tabular data.
  • Rigor in validation and experimentation, including the ability to identify misleading model improvements and explain error and uncertainty to non-technical audiences.
  • Experience deploying and monitoring production models on a cloud platform, such as AWS SageMaker or an equivalent.

Nice To Haves

  • Master's or PhD in Statistics, Computer Science, Economics, Operations Research, or a related field.
  • Experience modeling real estate, credit, or asset prices, including rent or valuation models, survival or renewal models, or credit risk.
  • Spatial data experience with tools or methods such as GeoPandas, PostGIS, H3, ArcGIS, drive-time analysis, or routing analysis.
  • MLOps experience, including faster inference, stable endpoints, or cost-efficient serving.
  • Experience building evaluations for LLM-based document extraction.
  • Hands-on experience with tabular foundation models, AutoML, or agent-assisted feature and hyperparameter search, including understanding where these approaches fail.
  • Familiarity with the AWS data stack, including Athena, S3, Glue, dbt, or Redshift.
  • Background in causal inference or econometrics.
  • Daily use of AI coding assistants such as Claude Code, Cursor, or similar, with the judgment to check their outputs.

Responsibilities

  • Retrain, improve, and extend rent, lease renewal, sale pricing, tenant credit, and entity de-duplication models.
  • Turn the record of past experiments, including failed experiments, into a research baseline.
  • Benchmark tabular foundation models, AutoML, and agent-driven automated research against well-tuned gradient-boosted baselines, adopting approaches only when they perform better on held-out, real-world outcomes.
  • Test candidate data sources and features—including drive time, location quality, zoning, site characteristics, and spatial layers—against actual leasing and sales outcomes.
  • Build backtesting, error analysis, and monitoring to verify model outputs before they reach decision-makers.
  • Design rigorous experiments using sealed holdouts, time- and location-aware splits, and multiple-comparison controls.
  • Maintain reproducible research through versioned training data, documented features, repeatable experiments, and updated model documentation.
  • Own model-serving endpoints, drift monitoring, and a model registry with clear lineage.
  • Keep batch prediction runs and SageMaker endpoints reliable and fast, and manage serving costs in line with usage.
  • Work with the AWS platform and deployment pipelines provided by the platform engineer.
  • Own the methodology for evaluating LLM extraction of lease and market-report data, including labeled datasets, calibrated automated graders, and regression definitions.
  • Translate questions from investment, research, and asset-management colleagues into analyses and explain uncertainty in plain language.
  • Represent Faropoint's models to investors and partners.
  • Track developments in machine learning and AI and bring back approaches useful to Faropoint's problems.
  • Work with the Director of Research to decide what to test next.
  • Mentor junior data scientists who help maintain the models.

Benefits

  • Discretionary bonus
  • Competitive healthcare benefits
  • Unlimited PTO
  • 401k match
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service