Remote Principal World Model Scientist - Housing Market

Zillow Group; United States; Remote; USD 196,000 - 312,000; Full time

Benefits offered by this job

Equity awards

Job summary

Zillow Group is seeking a Principal Applied Scientist to advance the World Model for housing markets. You will build demand representations from large-scale shopper data, design latent state-space and multi-tower models with calibrated uncertainty, and enable multi-step planning and forward/backward reasoning to inform home pricing and market dynamics.

You will also apply causal inference to observational data, lead open-ended research initiatives, and mentor scientists and ML engineers,

Qualifications

• PhD in Computer Science, Machine Learning, Statistics, Economics, or related field.
• Experience building latent state-space/world models (RSSM/Dreamer-family, JEPA-style latent prediction, or event-sequence transformers).
• Ability to turn large-scale user behavior data into structured demand representations while correcting for selection bias.
• Practical causal inference in observational settings and judgment about counterfactual claims.
• Proven record delivering open-ended research with leadership to scientists and MLEs.
• Strong programming skills, especially Python, plus ML frameworks (PyTorch, TensorFlow).

Responsibilities

• Build the demand layer of the World Model and turn shopper behavior into structured demand representations.
• Design and train latent state-space and sequential dynamics models with calibrated uncertainty.
• Estimate willingness-to-pay, per-home demand curves, and market clearing dynamics.
• Apply causal identification in observational data and define when a model must abstain from a claim.
• Contribute to the World Model evaluation battery and provide technical leadership and mentorship.

Skills

PhD in CS/ML

Latent state-space models

World models

Causal inference

Python

PyTorch

TensorFlow

Education

PhD in CS/ML/Statistics/Economics

Tools

PyTorch

TensorFlow

Python

Job description

Zillow Group is seeking a Principal Applied Scientist to advance the World Model for housing markets. You will build demand representations from large-scale shopper data, design latent state-space and multi-tower models with calibrated uncertainty, and enable multi-step planning and forward/backward reasoning to inform home pricing and market dynamics.

You will also apply causal inference to observational data, lead open-ended research initiatives, and mentor scientists and ML engineers,