Senior Applied Scientist, Property Analytics

Role overview Develop and lead production machine learning systems for property valuation and related lending decisions. The work spans research, model architecture, deployment, and ongoing performance management, with close collaboration among product, engineering, risk, and business specialists.

Responsibilities - Design, build, and deploy automated valuation models for lending products. - Develop statistical, machine learning, and deep learning approaches that account for location and time trends, economic conditions, market liquidity, and property risk. - Create frameworks to monitor model quality and support retraining as real estate conditions change. - Build analytical tools for teams working in risk, underwriting, and capital markets. - Collaborate with data infrastructure and MLOps teams on data capabilities, feature stores, and real-time model inference. - Develop useful features from structured and unstructured inputs, including property images, listing text, and geographic data; assess new AI methods and improve existing systems for scale and reliability.

Requirements - Master’s or Ph.D. in a quantitative field and substantial industry experience building and deploying production machine learning models; the posting specifies five or more years, or three or more with a Ph.D. - Demonstrated success developing statistical or machine learning models for customers, accounts, or property assets. - Applied expertise in advanced machine learning, deep learning, spatial analytics, or related AI methods. - Production programming experience in Python, SQL, and R. - Technical leadership and experience mentoring colleagues across disciplines. - Ability to explain mathematical and technical ideas clearly to nontechnical partners and senior leaders.

Nice to have Experience with automated valuation or appraisal systems; survival analysis, financial econometrics, or spatial-temporal forecasting; computer vision or natural language processing; distributed computing and deep learning frameworks; Bayesian methods, simulation, or causal machine learning; and MLOps, cloud infrastructure, feature stores, or model serving. Relevant financial risk or investment credentials are also welcomed.

Benefits and work setup The listing gives a remote base salary range of $175,000–$225,000 per year, plus bonus and benefits. Pay may vary by location and qualifications.