Applied Research Scientist, World Model
J
JobgetherAI and housing
Work from a location of your choice within the United States, subject to applicable geographic restrictions and remote work requirements.Full-Time
SalaryLocation-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.
Apply NowOpens the employer's application page
Job Details
- Required Skills
- PythonPyTorchTensorflow
Requirements
- PhD in Computer Science, Machine Learning, Statistics, Economics, or a related quantitative discipline.
- Hands-on experience building latent state-space models or world models, including belief-state representations, stochastic transition models, calibrated uncertainty, and multi-step rollout evaluation.
- Experience with world-model approaches such as RSSM/Dreamer-family architectures, JEPA-style latent prediction systems, or event-sequence transformers.
- 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.
- Practical causal-inference experience with observational data, including methods such as quasi-experiments, instrumental variables, or policy discontinuities.
- Strong programming skills, particularly in Python, and practical experience with PyTorch or TensorFlow.
- Track record of independently delivering open-ended research projects, defining scope, designing rigorous experiments, and translating ideas into measurable outcomes.
- Ability to guide research direction, collaborate with multidisciplinary teams, and provide technical leadership and mentorship.
- Strong familiarity with economic concepts is desirable, particularly market microstructure, search-and-matching models, structural demand estimation, discrete-choice models, and equilibrium feedback.
- Experience with agent-based modeling, market simulation, or simulation-based reinforcement learning is an advantage.
- Publications or other demonstrated research contributions in world models, model-based reinforcement learning, causal inference, or structural demand estimation are preferred.
Responsibilities
- Develop a foundational housing market model integrating supply, demand, consumer behavior, and macroeconomic factors.
- Transform large-scale shopper behavior data into structured demand representations and estimate willingness to pay.
- Design and train latent state-space, multi-tower, and sequential dynamics models for uncertainty-aware, multi-step predictions.
- Develop forward-looking and backward-planning models for listing strategies and seller objectives.
- Estimate demand curves, willingness-to-pay distributions, and market-clearing dynamics, connecting learned representations to economic quantities.
- Apply causal identification techniques to observational data, address selection bias, and assess when counterfactual predictions are unsupported.
- Develop evaluation frameworks for representations, forecasts, rollout stability, causal validity, and changing market conditions.
- Collaborate with research, product, engineering, platform, and data teams to align research with applications.
- Scope research questions, develop hypotheses, design experiments, interpret results, and translate findings into production-ready AI capabilities.
- Establish research direction, communicate findings, and mentor applied scientists and machine learning engineers.
View Full Description & ApplyYou'll be redirected to the employer's site
