Senior Applied Scientist, Property Analytics

Our Property Analytics team is made up of 360-degree thinkers that analyze complex problems and come up with creative solutions. We love to combine advanced analytics and machine learning skills with deep domain knowledge about the business when creating solutions. You will work with some of the most fascinating data sets in the world, alongside a world-class group of product engineers, sales and marketing leaders, and business operators.

Figure’s Property Analytics team is seeking a Senior Applied Scientist to join us in our effort to reinvent real estate lending. You will be working alongside engineering, product, and business leaders to tackle complex research and machine learning problems related to automated valuation models (AVMs), asset valuation, and process optimization.

An ideal candidate brings deep expertise in advanced machine learning, statistical modeling, and production-grade AI system architectures. You will lead technical direction, mentor team members, and partner closely with MLOps engineers, Product Managers, Credit Risk Management and Capital Markets subject matter experts to drive select strategic initiatives from initial research to production deployment. If you are keen on joining a dynamic company and solving intellectually challenging problems in a fast-paced environment, please reach out to us.

• →Lead the end-to-end design, architecture, development, and deployment of state-of-the-art automated valuation modeling (AVM) systems for novel lending products.
• →Architect and refine innovative machine learning, deep learning, and statistical models for asset valuation, incorporating spatial-temporal trends, macroeconomic factors, market liquidity, and property risk dynamics.
• →Establish robust quantitative frameworks for continuous model performance assessment, monitoring, and automated retraining across changing real estate cycles.
• →Build analytical tools and frameworks to empower cross-functional teams across risk, underwriting, and capital markets.
• →Partner closely with data infrastructure and MLOps engineering teams to drive initiatives that enhance data capabilities, build feature stores, and streamline real-time inference infrastructure.
• →Design useful data attributes and feature representations, leveraging structured, unstructured, and multimodal data sources (e.g., property photos, listing descriptions, spatial features).
• →Perform exploratory data analysis, evaluate frontier AI capabilities, and make strategic recommendations to improve current decisioning frameworks and valuation accuracy.
• →Refactor and optimize existing analytical solutions and algorithmic components to improve scalability, reliability, and execution efficiency.

• Ph.D. or Master's degree in a quantitative discipline (e.g., Computer Science, Data Science, Statistics, Economics, Applied Mathematics, Machine Learning) with 5+ years of industry experience (or 3+ years with a Ph.D.) building and deploying machine learning models in production.
• Proven track record of developing statistical and machine learning models at an account, customer, or real estate asset level.
• Solid understanding and hands-on application of advanced machine learning techniques, deep learning, spatial analytics, and AI capabilities.
• Strong production-level programming skills in Python, SQL, and R.
• Demonstrated experience in technical leadership, cross-functional collaboration, and mentoring junior team members.
• Excellent oral and written communication skills with the ability to explain complex technical, algorithmic, and mathematical concepts clearly to non-technical stakeholders and executive leadership.

• Hands-on experience developing, evaluating, and deploying Automated Valuation Models (AVMs) or automated appraisal systems.
• Exposure to time-to-event/survival analysis, financial econometric modeling, or spatial-temporal forecasting.
• Experience handling and modeling unstructured data, including computer vision or natural language processing applications in real estate.
• Proficiency with distributed computing frameworks (e.g., Spark) and modern deep learning frameworks (e.g., PyTorch, TensorFlow).
• Experience with Monte Carlo simulations, Bayesian inference, or causal machine learning.
• Familiarity with MLOps best practices, cloud architecture (AWS/GCP), feature stores, and model serving infrastructure.
• Progress towards or completion of relevant quantitative/financial certifications (e.g., FRM or CFA).

• If you are offered an interview or a role with Kiavi, this will be communicated with you through email, via an official email address ending in @kiavi.com or @lendinghome.com. 
• You will never be asked for payments of any kind during the process.
• We also never communicate with candidates via Whatsapp at any point during the recruitment process. 
• We won’t ask for personal information or data via text message. If you have any concerns regarding how genuine a text message is, please contact your recruiter.
• You can find our official Kiavi careers page here. We advise you to check that the page details and website addresses match if you have any concerns.

Kiavi is an Equal Opportunity Employer
San Francisco Fair Chance Ordinance Police Code, Article 49

We use E-Verify to confirm the identity and employment eligibility of all new hires.