Principal Applied Scientist (User Modeling)
New
Z
ZillowReal estate
U.S. employees may live in any of the 50 United States, with limited exceptions.Full-TimePrincipal
SalaryUSD 185800 - 312400 / year
Apply NowOpens the employer's application page
Job Details
- Required Skills
- PythonPyTorchTensorflow
Requirements
- PhD in Computer Science, Statistics, Economics, Machine Learning, or a related quantitative field.
- Depth in reinforcement learning or causal inference.
- Hands-on experience modeling user behavior at scale using sequence models over event streams, sessions, or trajectories.
- Experience predicting user intent or long-term outcomes.
- Practical depth in causal inference, including propensity scoring, treatment-effect estimation, or off-policy evaluation, or reinforcement learning applied to real sequential decision problems.
- Ability to independently scope and solve ambiguous problems end-to-end while providing technical leadership to scientists and MLEs.
- Working proficiency in Python and ML frameworks such as PyTorch or TensorFlow to run experiments and read, review, and debug code.
- Background in economics or econometrics, such as demand modeling or consumer choice, is a nice-to-have.
- Published work in RL, causal inference, survival analysis, or user modeling/simulation is a nice-to-have.
- Experience with generative sequence models or conditional language generation for behavioral or conversational simulation is a nice-to-have.
- Experience with rare-event modeling and probability calibration at scale is a nice-to-have.
- Familiarity with two-sided marketplaces, real estate, or long-horizon consumer journeys is a nice-to-have.
Responsibilities
- Own LLM post-training pipelines, including SFT, DPO, and reinforcement fine-tuning (RFT/GRPO), running training end-to-end on GPU infrastructure.
- Build and train multi-category reward models (PRMs) that emit scalar signals from contrastive preference pairs.
- Design on-policy and online assessment by scoring live agent trajectories using LLM-as-a-Judge frameworks.
- Translate offline evaluation rubrics into generalizable reward functions for production traces.
- Drive complex work end-to-end in collaboration with partner teams.
- Provide technical leadership and mentorship to scientists and MLEs.
- Help translate state-of-the-art AI research into production impact.
View Full Description & ApplyYou'll be redirected to the employer's site
