Intern – Tool-Augmented LLMs for CAD/BREP 3D Object Generation 🎓

The intern will join our AI and geometric modeling research team to explore how large language models (LLMs) can be enhanced with tool-augmented reasoning for generating high-quality 3D CAD/BREP objects. Reporting to a senior ML/geometry developer, this role focuses on integrating LLMs with geometry kernels (e.g., OpenCascade) to produce valid parametric designs, leveraging retrieval-augmented generation (RAG) for design reuse, and developing iterative refinement strategies to ensure manufacturability and geometric correctness. The intern will work at the intersection of generative AI, computational geometry, and CAD automation.

Responsibilities

• Investigate how LLMs can interface with CAD geometry kernels (e.g., OpenCascade) to generate valid BREP and parametric 3D models

• Develop tool-augmented reasoning pipelines that enable LLMs to call geometry APIs, validate shapes, and repair or refine generated models

• Explore retrieval-augmented generation (RAG) using prior CAD models, part libraries, or design templates

• Implement iterative refinement and adaptive test-time compute methods to enforce geometric, functional, or manufacturing constraints

• Evaluate generative outputs across metrics such as accuracy, validity, manufacturability, and similarity to relevant design priors

• Prototype end-to-end workflows for turning natural-language descriptions into CAD/BREP objects using LLMs + external tools

• Document research findings and develop actionable recommendations for integrating LLM-generated CAD designs into downstream engineering workflows