Applied Research Scientist, World Model

This position is listed on behalf of a partner company, which manages all applications and next steps. Our partner is looking for an Applied Research Scientist, World Model based in the United States.

The Applied Research Scientist, World Model will advance foundational AI research by developing a unified model that captures housing market dynamics, consumer demand, and economic conditions. This role focuses on transforming large-scale user behavior data into predictive representations that enable more reliable, uncertainty-aware market simulations. You will design sophisticated machine learning systems capable of answering complex, multi-step questions about home pricing, listing strategies, and expected market outcomes. Working at the intersection of machine learning, causal inference, and economics, you will help bridge cutting-edge research and practical consumer applications. Collaborating with research scientists, engineers, product teams, and data specialists, you will shape the technical direction of an emerging AI capability. This fully remote opportunity offers substantial research ownership, technical leadership, and the chance to influence how people make important housing decisions through intelligent, data-driven insights. \n

Accountabilities

World Model Research and Development:

Design, develop, and advance a foundational housing market model that integrates supply, demand, consumer behavior, and macroeconomic factors into a consistent representation of market conditions. Consumer Demand Modeling:

Transform large-scale shopper behavior data, including search activity, engagement patterns, and session trajectories, into structured demand representations. Develop methods to translate consumer attention into measurable demand and estimate willingness to pay. Advanced Machine Learning Model Development:

Design and train latent state-space models, multi-tower architectures, and sequential dynamics models capable of representing evolving market conditions, modeling uncertainty, and supporting multi-step predictions. Forward and Backward Planning:

Develop models that support forward-looking scenarios, such as estimating how listing prices influence selling timelines, and backward-planning scenarios that identify strategies for achieving specific seller objectives. Economic Modeling and Market Dynamics:

Estimate home-level demand curves, willingness-to-pay distributions, and market-clearing dynamics. Connect learned representations to meaningful economic quantities and account for feedback between buyers, sellers, and market conditions. Causal Inference and Counterfactual Reasoning:

Apply causal identification techniques to observational data, distinguish causal relationships from correlations, address selection bias in platform-observed populations, and determine when the model should abstain from making unsupported counterfactual predictions. Model Evaluation and Validation:

Develop and contribute to evaluation frameworks covering internal state representations, calibrated multi-target forecasts, multi-step rollout stability, causal validity, and performance under unfamiliar or changing market conditions. Cross-Functional Research Collaboration:

Partner with researchers focused on listing-state modeling, market simulation, and evaluation, as well as product, engineering, platform, and data teams, to align research priorities with real-world applications. End-to-End Research Ownership:

Independently scope ambiguous research questions, develop hypotheses, design experiments, interpret results, and translate findings into reliable, production-ready AI capabilities. Technical Leadership and Mentorship:

Establish research direction, communicate complex technical findings, mentor applied scientists and machine learning engineers, and contribute to the advancement of world models, causal machine learning, and economic modeling. Requirements

Education:

PhD in Computer Science, Machine Learning, Statistics, Economics, or a related quantitative discipline. World Model Expertise:

Hands-on experience building latent state-space models or world models, such as RSSM/Dreamer-family architectures, JEPA-style latent prediction systems, or event-sequence transformers. Experience should include belief-state representations, stochastic transition models, calibrated uncertainty, and multi-step rollout evaluation rather than single-target forecasting alone. Consumer Behavior and Demand Modeling:

Demonstrated ability to transform large-scale behavioral data into structured demand representations, including utility estimation, willingness-to-pay modeling, and funnel or conversion analysis. Experience correcting for selection bias in platform-observed populations is essential. Causal Inference:

Practical experience applying causal inference methods to observational data, including quasi-experiments, instrumental variables, or policy discontinuities. Strong judgment is required to distinguish reliable causal conclusions from correlations that do not justify counterfactual claims. Programming and Machine Learning:

Strong programming skills, particularly in Python, and practical experience with machine learning frameworks such as PyTorch or TensorFlow. Research Execution:

A proven track record of independently delivering open-ended research projects, defining problem scope, designing rigorous experiments, and translating novel ideas into measurable outcomes. Technical Leadership:

Demonstrated ability to guide research direction, collaborate with multidisciplinary teams, and provide technical leadership and mentorship to scientists and machine learning engineers. Economics and Market Modeling:

Strong familiarity with economic concepts is highly desirable, particularly market microstructure, search-and-matching models, structural demand estimation, discrete-choice models, and equilibrium feedback. Simulation and Reinforcement Learning:

Experience with agent-based modeling, market simulation, or simulation-based reinforcement learning is an advantage. Research Contributions:

Publications or other demonstrated research contributions in world models, model-based reinforcement learning, causal inference, or structural demand estimation are preferred. Advanced Data and Representation Learning:

Familiarity with multimodal representation learning or bitemporal, leakage-safe training data is beneficial. Marketplace or Real Estate Experience:

Experience with two-sided marketplaces, real estate platforms, or long-horizon consumer journeys is a plus. Analytical and Communication Skills:

Strong quantitative reasoning, critical thinking, and the ability to explain complex research concepts clearly to technical and nontechnical stakeholders. Adaptability and Independence:

Comfort working in an emerging research area where problems are ambiguous, experimentation is essential, and solutions require both scientific rigor and practical judgment. Benefits

Competitive Compensation:

Location-dependent annual base salary ranges:

$195,600–$312,400

in California, Connecticut, Maryland, Massachusetts, New Jersey, New York, Washington State, and Washington, D.C. $185,800–$296,800

in Colorado, Hawaii, Illinois, Maine, Minnesota, Nevada, Ohio, Rhode Island, Vermont, and Virginia. Compensation for other eligible U.S. locations may differ. Final offers depend on experience, skills, qualifications, performance-related factors, and geographic location.

Equity Awards:

Eligibility for equity awards in addition to base salary, subject to applicable program terms and factors such as experience, performance, and location. Fully Remote Work:

Work from a location of your choice within the United States, subject to applicable geographic restrictions and remote work requirements. Distributed Work Culture:

A flexible working model built around trust, collaboration, and clear systems, enabling employees to contribute effectively from different locations. Research Ownership:

The opportunity to shape foundational AI research, influence technical architecture, and develop new approaches to market simulation and predictive modeling. Professional Growth:

Opportunities to deepen expertise in world models, machine learning, causal inference, economic modeling, and advanced AI applications. Technical Leadership:

The chance to mentor researchers, collaborate with experienced multidisciplinary teams, and influence the development of emerging AI technologies. Meaningful Impact:

Apply advanced research to real-world housing challenges and help consumers make more informed decisions about buying and selling homes. Inclusive Work Environment:

Join a collaborative culture that values innovation, diverse perspectives, professional development, and equal employment opportunity. \n

How Jobgether works: We use an

AI-powered matching process

to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team. We appreciate your interest and wish you the best! Why Apply Through Jobgether? Data Privacy Notice:

By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time. #LI-CL1