Applied Research Scientist, World Model

What you'll do

• Build the demand layer of the World Model by converting large-scale shopper behavior into structured demand representations.
• Design and train latent state-space, multi-tower, and sequential dynamics models with calibrated uncertainty for multi-step rollouts.
• Estimate willingness-to-pay, per-home demand curves, and market clearing dynamics using learned representations.
• Apply causal identification in observational data to determine when correlations support "what-if" claims.
• Contribute to the World Model evaluation battery, including state probes, multi-target forecasts, and causal checks.
• Drive ambiguous research projects end-to-end and provide technical leadership to scientists and machine learning engineers.

What we're looking for

• Must have a PhD in Computer Science, Machine Learning, Statistics, Economics, or a related quantitative field.
• Must have hands-on experience building latent state-space or world models, including belief-state representations and stochastic transition models.
• Must have experience turning large-scale user behavior data into structured demand representations while correcting for selection bias.
• Must have practical experience in causal inference for observational settings and identifying counterfactual claims.
• Must have a proven record of delivering on open-ended research projects and providing technical leadership to scientists and MLEs.
• Must have strong programming skills in Python and experience with ML frameworks like PyTorch or TensorFlow.
• Economics fluency in market microstructure, search-and-matching, or structural/discrete-choice demand models (preferred).
• Experience with agent-based or market simulation, simulation-based reinforcement learning, or published work in world models (preferred).