AI Real Estate Valuation Engineer

Valtrix Solutions

Remote · $130k – $160k / year · Full-time · Posted 4 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Automated property valuation models (AVMs) are used by banks, insurers, and real estate platforms to estimate property values without a physical appraisal. Our AVM is used for 2 million valuations per year, and being 5% more accurate than the competition means our clients save billions in risk-adjusted capital. You'll lead model development for our AVM: combining structured data (comparable sales, tax records, property features) with unstructured signals (satellite imagery, neighborhood text descriptions, local market sentiment). The model ensemble uses gradient boosting for structured features and deep learning for unstructured inputs. Accuracy and explainability are equally important — regulators require that every valuation be explainable, so you'll also build the interpretability layer that tells a bank examiner exactly why a property was valued at a specific number.

Fully remote.

Responsibilities

Lead development of automated property valuation models
Combine structured and unstructured data signals in ensemble architectures
Build explainability features for regulatory compliance
Design evaluation frameworks measuring valuation accuracy by geography and property type
Present model methodology to banking regulators and client risk teams

Requirements

5+ years in ML or data science with real estate or financial modeling experience
Strong PyTorch and scikit-learn skills for ensemble model development
Experience with model interpretability techniques (SHAP, partial dependence)
SQL proficiency for large-scale property data analysis
Comfort presenting technical methodology to non-technical regulators