Senior Applied Scientist - Remote Reward Modeling

ZINC Zillow, Inc.; United States; Remote; USD 140,000 - 240,000; Full time

Job summary

Zillow Group is hiring a Senior Applied Scientist for the Agentic Foundations team to own LLM post-training pipelines and build reward models that drive production impact. You will work across product, engineering, science, and data teams to translate advances in LLMs and RL into scalable systems, operating in a remote-capable environment.

The role emphasizes leadership, end-to-end delivery, and collaboration across diverse teams to advance agentic AI for home-shopping experiences at scale.

Qualifications

• Master's degree or higher in Computer Science or related field.
• Hands-on experience with LLM post-training and RL fine-tuning.
• Exposure to reward model development; production deployment not required.
• Strong knowledge of generative AI, transformers, RL, and preference learning.
• Ability to scope ambiguous problems end-to-end and mentor scientists.
• Strong Python skills; experience with PyTorch or TensorFlow.

Responsibilities

• Own LLM post-training pipelines — SFT, DPO, and RFT, running end-to-end training on GPU infrastructure.
• Build and train multi-category reward models emitting scalar signals from contrastive preference pairs.
• Design on-policy and online assessment using LLM-as-a-Judge frameworks.
• Translate offline evaluation rubrics into generalizable reward functions for production traces.
• Independently drive complex work end-to-end by collaborating across partner teams.
• Provide technical leadership and translate state-of-the-art AI research into production impact.

Skills

LLM post-training

RL fine-tuning

Python

PyTorch

TensorFlow

Technical leadership

Education

Master's degree in CS

Tools

Databricks

Fireworks

Job description

Zillow Group is hiring a Senior Applied Scientist for the Agentic Foundations team to own LLM post-training pipelines and build reward models that drive production impact. You will work across product, engineering, science, and data teams to translate advances in LLMs and RL into scalable systems, operating in a remote-capable environment.

The role emphasizes leadership, end-to-end delivery, and collaboration across diverse teams to advance agentic AI for home-shopping experiences at scale.