PhD Researcher, Agentic 3D Modeling in Immersive Environments

Autodesk•Boston, MA

2d•$118,560 - $162,240

About The Position

As a Research Intern at Autodesk Research, you will explore and apply novel technologies and techniques to help customers design and build a better, safer, and more sustainable world. You will work with a multidisciplinary research team across AI, spatial computing, architecture, engineering, and construction (AEC), and human perception to develop and evaluate methods that connect different representations of the built environment within immersive, editable world models. Potential research directions include editing non-traditional 3D geometries such as Gaussian splats, building multilayered spatial representations of architectural spaces, and controlling 3D modeling and design environments and processes with agentic workflows. You will build research prototypes and explore how this work could inform future Autodesk design workflows. The 2027 Research Internship Program is a paid, 16-week program running from May 24 to September 10, 2027. Internships follow Autodesk’s Flexible Workplace approach, supporting office, remote, and hybrid work based on business and team needs.

Requirements

Currently pursuing a PhD in Computer Science, Machine Learning, Computer Graphics, Computational Design, or a related field, with a completion date in 2028 or later.
Research experience in AI/ML, computer vision, reality capture and 3D reconstruction, 3D modeling or geometry generation, or a related computational field.
Strong programming skills, ideally with Python and modern machine learning frameworks.
Experience designing computational experiments and working with complex datasets.
Strong collaboration and communication skills.
Track record of contributions to the field, demonstrated through related projects, open-source work, or publications.

Nice To Haves

Experience in multimodal AI or vision-language models.
Experience with world models, AI agents, or spatial intelligence.
Experience with 3D, simulation, or virtual environments.
Experience with human perception or human-centered AI.
Experience with modern 3D modeling and reconstruction methods.
Experience with AEC or computational design.
Solid understanding of 3D modeling systems and data pipelines.

Responsibilities

Research multimodal AI approaches for generating and editing novel 3D representations of built environments.
Develop methods using foundation models, AI agents, and/or world models.
Work with multimodal datasets, including visual, spatial, behavioral, and physics simulation data.
Design experiments and benchmarks to evaluate AI predictions against human responses.
Build and evaluate research prototypes for real and simulated environments.
Document and communicate findings through papers, presentations, and demonstrations.