Senior User Modeling Scientist — Remote (RL & Causal)

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

Benefits offered by this job

Equity awards

Flexible work arrangement

Job summary

Zillow Group Inc. is seeking an Applied Scientist to own LLM post-training pipelines and develop reward models at scale, focusing on user modeling and real-world home-shopping tasks.

The role collaborates with product, engineering, science, platform, and data teams to translate advances into production impact. This remote position offers CloudHQ flexibility, with base pay ranges by location and equity awards.

Qualifications

• PhD in CS, stats, econ, ML, or related field with depth in RL or causal inference.
• Hands-on experience modeling user behavior at scale: sequences, sessions, trajectories.
• Depth in causal inference or RL for sequential decision problems.
• Ability to scope and solve ambiguous problems end-to-end while leading scientists/ML engineers.
• Proficiency in Python and ML frameworks (PyTorch or TensorFlow).

Responsibilities

• Own LLM post-training pipelines — SFT, DPO, and reinforcement fine-tuning on GPU infrastructure.
• Build and train fast, multi-category reward models from contrastive preference pairs.
• Design on-policy and online assessment to score live agent trajectories.
• Provide technical leadership and mentorship across partner teams.

Skills

Reinforcement learning

Causal inference

Python

PyTorch

TensorFlow

Sequence modeling

Education

PhD in CS/Stats/ML

Tools

PyTorch

TensorFlow

Job description

Zillow Group Inc. is seeking an Applied Scientist to own LLM post-training pipelines and develop reward models at scale, focusing on user modeling and real-world home-shopping tasks.

The role collaborates with product, engineering, science, platform, and data teams to translate advances into production impact. This remote position offers CloudHQ flexibility, with base pay ranges by location and equity awards.