AI Applied Scientist - PhD Intern, Next-Gen Agentic and Multi-Modal Home Exploration Experience
Skip the busywork
ApplyBolt rewrites your resume for this exact role and hits submit. You just pick the jobs.
About this role
About the team
Are you passionate about creating AI agents capable of reasoning, planning, and collaborating in real-world situations? The Zillow AI Applied Science team is dedicated to developing the next generation of agentic systems, powered by large foundation models, to assist customers in exploring , finding, and dreaming their ideal homes. With millions of users actively seeking the best way to shop for their next home, we are focused on building a cutting-edge online shopping experience. At the convergence of research, engineering, and product, we design AI agents that execute meaningful actions in multi-stakeholder environments. These agents achieve this by comprehending user needs and data, maintaining context, and optimizing for the customer-facing experience.
Some of the questions we are asking in this new paradigm are: How can AI analyze complex user interactions within the UX to determine and suggest the most effective next steps for users? What is the optimal collaborative approach between AI and users to achieve the established objectives?
About the role
We are seeking remote PhD interns for Summer 2026!
As an intern, you will use your expertise in Agentic systems, conversational AI, LLMs, and multi-modal inference to advance customer-facing experiences and interfaces. Your research will help build AI agents capable of handling complex, rich media oriented, multi-turn interactions while maintaining context and taking appropriate actions. Your internship will develop the next-generation real estate shopping experience that integrates Agentic and Multi-modal reasoning to transform how users find their ideal homes through pushing research problems including but not limited to:
- Personalized and Guided Home Exploration: An agentic approach that proactively guides and helps users navigate millions of listings to identify the best homes, the experience should be highly engaging, fun and goal oriented
- Conversational Optimization: Enhanced multi-turn conversations with effective context management and improved dialogue quality, achieved through organized data from retrieved results
- Multi-modal Collaboration System: A combination of 3D computer vision (utilizing 3D reconstructions and Gaussian splats) and LLM interfaces, powered by conversational AI
This role has been categorized as a Remote position. “Remote” employees do not have a permanent corporate office workplace and, instead, work from a physical location of their choice, which must be identified to the Company. U.S. employees may live in any of the 50 United States, with limited exceptions.
In California, Connecticut, Maryland, Massachusetts, New Jersey, New York, Washington state, and Washington DC the standard base pay range for this role is $104,000.00 - $166,000.00 annually. This base pay range is specific to these locations and may not be applicable to other locations.
In Colorado, Hawaii, Illinois, Minnesota, Nevada, Ohio, Rhode Island, and Vermont the standard base pay range for this role is $104,000.00 - $166,000.00 annually. The base pay range is specific to these locations and may not be applicable to other locations.
Who you are
- Currently enrolled in a PhD program in computer science, NLP, machine learning, or a related field, with solid publication record
- Background in at least one of the following areas:
- Human computer interaction (HCI)
- User behavior research in the context of agentic AI
- Agentic AI (tool use, planning, reasoning, decision-making)
- Conversational AI and dialogue optimization
- Multi-modal inference models with focus on combining 3D Computer Vision and LLMs
- Multi-agent systems and orchestration
- Memory systems and context engineering
- Reinforcement learning and reward modeling
- Familiarity with modern deep learning frameworks (e.g., PyTorch, Hugging Face Transformers)
- Strong research mindset, with motivation to publish
- Interest in applying AI to complex, multi-stakeholder domains
Here at Zillow - we value the experience and perspective of candidates with non-traditional backgrounds. We encourage you to apply if you have transferable skills or related experiences.