Senior Applied Scientist (Post-Training)

Role and responsibilities:

• Own LLM post-training pipelines — SFT, DPO, and reinforcement fine-tuning (RFT/GRPO) — running training end-to-end on GPU infrastructure.

• Build and train fast, multi-category reward models (PRMs) that emit scalar signals from contrastive preference pairs.

• Design on-policy and online assessment: score live agent trajectories using LLM-as-a-Judge frameworks.

• Translate offline evaluation rubrics into generalizable reward functions that work on arbitrary production traces.

• Independently drive complex work end-to-end by collaborating across partner teams.

• Provide technical leadership and mentorship while helping translate state-of-the-art AI research into production impact.

In Colorado, Hawaii, Illinois, Maine, Minnesota, Nevada, Ohio, Rhode Island, Vermont, and Virginia the standard base pay range for this role is $156,200.00 - $249,400.00 annually. The base pay range is specific to these locations and may not be applicable to other locations.

At Zillow, we’re reimagining how people move—through the real estate market and through their careers. As the most-visited real estate platform in the U.S., we help people navigate buying, selling, financing and renting with greater ease and confidence. Whether you're working in tech, sales, operations, or design, you’ll be part of a company reshaping an industry and helping more people make home a reality.

How we work is a key part of that transformation. Through Cloud HQ, our strategic approach to distributed work, most employees have the flexibility to work from wherever they’re most productive—enabling us to move fast, stay connected and deliver on our people promise. 

Zillow is honored to be recognized among the best workplaces in the U.S. Zillow was named one of FORTUNE 100 Best Companies to Work For® in 2026, and included on TIME’s America’s Best Companies 2026 list, reflecting our commitment to creating an innovative, inclusive, and engaging culture where employees are empowered to grow.

No matter where you sit in the organization, your work will help drive innovation, support our customers, and move the industry—and your career—forward, together.

Zillow Group is an equal opportunity employer committed to fostering an inclusive, innovative environment with the best employees. We are committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity or Veteran status. If you have a disability or special need that requires accommodation, please contact your recruiter directly.

Qualified applicants with arrest or conviction records will be considered for employment in accordance with applicable state and local law.

Los Angeles County applicants: Job duties for this position include: work safely and cooperatively with other employees, supervisors, and staff; adhere to standards of excellence despite stressful conditions; communicate effectively and respectfully with employees, supervisors, and staff to ensure exceptional customer service; and follow all federal, state, and local laws and Company policies. Criminal history may have a direct, adverse, and negative relationship with some of the material job duties of this position. These include the duties and responsibilities listed above, as well as the abilities to adhere to company policies, exercise sound judgment, effectively manage stress and work safely and respectfully with others, exhibit trustworthiness and professionalism, and safeguard business operations and the Company’s reputation. Pursuant to the Los Angeles County Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records.

• Master's degree or higher in Computer Science or a related field.

• Hands-on experience with LLM post-training and RL fine-tuning: SFT, DPO, RFT/GRPO, running end-to-end training runs on GPU infrastructure.

• Exposure to reward model development — research-level experience is sufficient; production deployment is not required.

• Strong knowledge of generative AI, including foundation models, transformers, reinforcement learning, and preference learning.

• Ability to independently scope and solve ambiguous problems end-to-end while providing technical leadership to scientists and MLEs.

• Strong programming skills, especially Python, plus experience with ML frameworks such as PyTorch or TensorFlow.

Nice-to-haves:

• PhD in Computer Science, Machine Learning, or a related field.

• Experience evaluating agentic AI: multi-turn trace analysis, LLM-as-a-Judge, and the interaction between offline evals and online monitoring.

• Published work in post-training, RLHF/RLAIF, preference learning, or reward modeling.

• Experience with GPU training platforms such as Databricks or Fireworks.