Work Learn | GenAI & LLM-Enabled Co-Design Research Assistant
Overview of duties
Research assistant will support a project on GenAI- and LLM-enabled co-creation for architectural / urban design and public engagement.
The role focuses on three cutting-edge workflows:
(1) natural-language-driven automated 3-D modelling;
(2) GenAI-assisted architectural visualization; and
(3) AI-assisted co-design interface.
The position suits senior undergraduate or graduate students who are proficient with Grasshopper and curious about new AI technologies.
Tasks and Duties
The research assistant will work on three innovative AI workflows:
AI-assisted 3D modelling – Extend existing Rhino / Grasshopper workflows that turn natural-language prompts into digital models (parametric massing, streetscape, or terrain). Create scenario-based demos and improve documentation; work is highly experimental.
AI-assisted architectural visualization – Fine-tune generative-AI pipelines to convert design iterations into renderings and archive the process for future teaching and research.
AI-assisted public engagement – Explore interfaces that make AI design tools more accessible to the public, with the option of developing a prototype for an exhibition.
The supervisor Xun Liu will provide weekly meetings for goal-setting and code review, along with established workflows and learning resources. Tasks progress from replicating provided examples to independent experimentation and integration of all three workflows into a cohesive public engagement demonstration.
The work is highly experimental and requires strong problem-solving skills, creativity, and the ability to work independently while maintaining clear documentation practices.
Qualifications
Education level: Senior undergraduate (Year 3 or 4) or graduate students in Architecture, Landscape Architecture, or Urban Design. Must have completed at least one computation-focused design course (e.g., DM II, ARCH 577C, or DES 450I: Coding for Designers).
Previous skills/knowledge required for success in this position: Students must demonstrate proven fluency with Rhino and Grasshopper. Preferred qualifications include working knowledge of Python, experience with generative AI tools such as Stable Diffusion, and familiarity with physical computing platforms. Additional assets include clear documentation practices, strong problem-solving abilities, creative debugging approaches, and solid version-control habits.
Students should show curiosity about emerging AI technologies and their applications in design, along with strong communication skills for potential community engagement work.
Application deadline
How to apply
Please email resume and cover letter explaining your unique skills and qualifications for this role, including specific examples of your Rhino/Grasshopper experience and any prior work with AI tools or computational design.
In addition, include a maximum of 3 annotated images of your work that demonstrate your computational design skills and creative problem-solving abilities.