PhD Researcher, Predictive Agentic Systems for Building Design

Job Requisition ID # 26WD101631 Position Overview As a Research Intern at Autodesk Research, you will explore and apply novel technologies and techniques to empower our customers in designing and building a better, safer, and more sustainable world. We are a team of researchers, engineers, and industry domain experts working on projects that range from learning-based design systems, computer vision, graphics, robotics, human-computer interaction, sustainability, simulation, manufacturing, architectural design and construction. Working with a multidisciplinary research team across AI, AEC and design, you'll develop and evaluate agentic workflows that help people and AI agents understand the consequences of design and construction decisions, answering "what happens if I change this?" quickly and reliably. Possible research directions may include training world models, such as Joint-Embedding Predictive Architectures (JEPA), that predict the outcomes of design actions; coordinating multi-agent systems and agent swarms that explore, critique and refine many design alternatives at once; and combining agents with fast, structured decision models that make reliable judgments in real time. You'll build research prototypes, develop evaluation methods and benchmarks, and explore how this research could inform future Autodesk design workflows. Responsibilities Research agentic workflows for AEC design and construction. Develop methods using world models, multi-agent systems, and/or fast