# Daniele Grandi — Profile > A single-file knowledge base summarizing Daniele Grandi's profile, work, projects, publications, patents, and repositories. > > This document mirrors the content of [grndnl.github.io](https://grndnl.github.io/) and is intended to be fed to LLMs and AI agents so they can answer questions about Daniele's background, research, and work. > > Source of truth for the website: > Auto-generated: 2026-05 (do not edit by hand — see scripts/build_agents_md.rb) --- ## Identity & Contact - **Name:** Daniele Grandi - **Pronunciation (IPA):** [daˈɲɛ.lɛ ˈɡran.di] (Dani) - **Current role:** Principal Research Scientist, [Autodesk Research](https://www.research.autodesk.com/) - **Focus areas:** Machine Learning + Design Research - **Location:** South Lake Tahoe, CA, 96150 | also affiliated with San Francisco, CA - **Email:** grndnl@gmail.com - **Website:** - **Autodesk Research profile:** - **LinkedIn:** - **Google Scholar:** - **GitHub:** [grndnl](https://github.com/grndnl) and [danielegrandi-adsk](https://github.com/danielegrandi-adsk) ## About _The narrative below is in Daniele's own first-person voice, copied verbatim from the website's about page._ As a Principal Research Scientist at Autodesk Research, I'm working to further the machine understanding of mechanical design problems. I'm interested in leveraging machine learning, knowledge representation and reasoning, LLMs, knowledge graphs, and agentic AI to create the next generation of conceptual and detail design tools. In collaboration with UC Berkeley, CMU, Oregon State University, and MIT, we are researching methods to learn design best practices from CAD datasets, and releasing ML benchmarks to expose model biases in design tasks and foster industry and academic innovation. At Autodesk, I've also worked as a Design Engineer on generative design research prototypes. Previously, I worked as an engineering consultant for a metal AM startup, focusing on design, simulation, and optimization of assemblies for AM. I graduated from UC Berkeley with a Mechanical Engineering degree. I started working with 3D printers at Berkeley, where I founded the 3D Modeling Club. While additive manufacturing had been my main field of focus, I also enjoyed traditional manufacturing methods, applied to mechatronics projects. I enjoy getting my hands on all parts of a project, whether it involves design, coding, circuits, or fabrication. The first 3D printing startup that I joined was eucl3D, a Berkeley startup working with game developers to provide custom high-quality 3D printed collectibles. Through Project BAM, the second 3D printing startup I worked at, I learned more about metal additive manufacturing and became interested in design optimization. ## Education | Degree | Institution | Field | Dates | |---|---|---|---| | Master | University of California, Berkeley | Information and Data Science | 2022-01 – 2023-12 | | Bachelor of Science | University of California, Berkeley | Mechanical Engineering | 2011-08 – 2015-05 | ## Work Experience ### Autodesk — Principal Research Scientist *San Francisco, CA / Remote · 2024-11 – Present* Researching machine learning applications in data-driven design using LLMs, VLMs, and GNNs. Collaborating with MIT, UC Berkeley, and CMU on datasets and benchmarks. ### Autodesk — Sr. Research Engineer *San Francisco, CA / Remote · 2019-03 – 2024-11* Focused on combining mechanical engineering with machine learning, leveraging knowledge graphs and semantic technologies to extract best practices from CAD data. ### Autodesk — Design Engineer *San Francisco, CA / London, UK · 2015-09 – 2019-03* Worked on generative design platforms, creating demonstrators and integrating end-user feedback into development. ### Project BAM — Additive Manufacturing Engineer *San Francisco, CA · 2015-05 – 2016-03* Streamlined additive manufacturing processes, designed facility layout, and supported customer part redesign for AM. ## Skills - **Programming:** Python, C++, MATLAB, Visual Basic - **Data Science:** Pytorch, Tensorflow, Keras, Scikit-learn, R, SQL, Neo4j, GDL, GNN, NLP - **CAD:** Autodesk Expert Elite, SolidWorks Certified Professional, NX, Creo (Pro/E) - **Simulation:** NASTRAN, Siemens Femap, Autodesk Simulation Mechanical, CFD - **Optimization:** Generative Design/TopOpt, ADSK Within, Altair Optistruct, Solidthinking Inspire - **Manufacturing:** Additive Manufacturing, Machine Shop Expertise ## Featured Projects A selection of projects. For the latest research work, see Publications below. - **Generative AI for Assembly Design** — How can Generative AI design tools be used to design assemblies, from coffee makers to EVs? — [Link](https://conferences.autodesk.com/flow/autodesk/au2025/sessioncatalog/page/digitalpublic/session/1753737394288001KjDm) - **Clean data is all you need** — Process PDFs of scientific papers into structured data. — [Link](https://github.com/grndnl/clean_data_is_all_you_need) - **6 DoF object pose estimation** — Edge implementatinon of estimation from monocular 2D images. — [Link](https://github.com/grndnl/edge_6DoF_estimation/tree/main) - **AI-assisted Knowledge Graph Design** — Research collaboration with CSUN, NIST, and NASA JPL to implement a recommendation system for materials of part in assemblies. — [Link](https://arcs.center/ai-assisted-knowledge-graph-design-for-the-cadre-robots/) - **Dreamcatcher** — Generative design research prototype, democratizing topology optimization. — [Link](https://www.research.autodesk.com/projects/project-dreamcatcher/) - **Hackrod** — Generatively design manufacturable car chassis. — [Link](https://www.youtube.com/watch?v=0ebsf2BMYm8) - **Concept Interplanetary Lander** — Research collaboration with NASA JPL leveraging generative design for space exploration. — [Link](https://www.research.autodesk.com/projects/gamma-space-exploration-lander/) - **Generative Quadcopter** — Quadcopter chassis designed using generative design research prototype software. — [Link](https://www.youtube.com/watch?v=CtYRfMzmWFU) - **F1 Suspension** — Generative design of F1 suspension. — [Link](https://labs.blogs.com/its_alive_in_the_lab/2019/01/autodesk-gallery-at-autodesk-university-in-las-vegas-engineering-for-formula-1.html) - **Modular chaiR** — Modular chair design for synthetic data generation and fabrication. — [Link](https://www.instructables.com/Modular-CHAIR/) - **Olsryd 9 Cylinder Radial Engine** — Design of complete assembly of an airplane engine composed of more 1600 parts. — [Link](https://www.autodesk.com/community/gallery/project/25350/olsryd-9-cylinder-radial-engine) ## GitHub Repositories GitHub users: - [grndnl](https://github.com/grndnl) - [danielegrandi-adsk](https://github.com/danielegrandi-adsk) Featured repositories: - [grndnl/llm_material_selection_jcise](https://github.com/grndnl/llm_material_selection_jcise) - [grndnl/clean_data_is_all_you_need](https://github.com/grndnl/clean_data_is_all_you_need) - [VincenzoFerrero/OSDR-GNN](https://github.com/VincenzoFerrero/OSDR-GNN) - [danielegrandi-adsk/IDETC23-Autodesk-hackathon](https://github.com/danielegrandi-adsk/IDETC23-Autodesk-hackathon) - [grndnl/edge_6DoF_estimation](https://github.com/grndnl/edge_6DoF_estimation) ## Selected Publications Highlighted as "selected" on the website. See the full list below or [Google Scholar](https://scholar.google.com/citations?user=X0qp478AAAAJ&hl=en) for the most up-to-date list. - **Designqa: A multimodal benchmark for evaluating large language models’ understanding of engineering documentation** — Anna C Doris, Daniele Grandi, Ryan Tomich, Md Ferdous Alam, Mohammadmehdi Ataei, Hyunmin Cheong, et al. *Journal of Computing and Information Science in Engineering 25(2):021009*, 2025. *(Dataset)* - **Evaluating large language models for material selection** — Daniele Grandi, Yash Patawari Jain, Allin Groom, Brandon Cramer, Christopher McComb *Journal of Computing and Information Science in Engineering 25(2):021004*, 2025. *(LLM)* - **What’s in a Name? Evaluating Assembly-Part Semantic Knowledge in Language Models Through User-Provided Names in Computer Aided Design Files** — Peter Meltzer, Joseph G Lambourne, Daniele Grandi *Journal of Computing and Information Science in Engineering 24(1):011002*, 2024. *(LLM)* - **HG-CAD: hierarchical graph learning for material prediction and recommendation in computer-aided design** — Shijie Bian, Daniele Grandi, Tianyang Liu, Pradeep Kumar Jayaraman, Karl Willis, Elliot Sadler, et al. *Journal of Computing and Information Science in Engineering 24(1):011007*, 2024. *(Graph Neural Network)* - **Elicitron: An LLM agent-based simulation framework for design requirements elicitation** — Mohammadmehdi Ataei, Hyunmin Cheong, Daniele Grandi, Ye Wang, Nigel Morris, Alexander Tessier *arXiv preprint arXiv:2404.16045*, 2024. *(LLM)* - **Conceptual design generation using large language models** — Kevin Ma, Daniele Grandi, Christopher McComb, Kosa Goucher-Lambert *International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (American Society of Mechanical Engineers)*, 2023. *(LLM)* - **Material prediction for design automation using graph representation learning** — Shijie Bian, Daniele Grandi, Kaveh Hassani, Elliot Sadler, Bodia Borijin, Axel Fernandes, et al. *International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (American Society of Mechanical Engineers)*, 2022. *(Graph Neural Network)* - **Joinable: Learning bottom-up assembly of parametric cad joints** — Karl DD Willis, Pradeep Kumar Jayaraman, Hang Chu, Yunsheng Tian, Yifei Li, Daniele Grandi, et al. *Proceedings of the IEEE/CVF conference on computer vision and pattern recognition*, 2022. *(Machine Learning)* - **Conversion of geometry to boundary representation with facilitated editing for computer aided design and 2.5-axis subtractive manufacturing** — Karl Darcy Daniel Willis, Nigel Jed Wesley Morris, Andreas Linas Bastian, Adrian Adam Thomas Butscher, Daniele Grandi, Suguru Furuta, et al. 2022. *(Patent)* ## Full Publication List ### 2025 - **Designqa: A multimodal benchmark for evaluating large language models’ understanding of engineering documentation** — Anna C Doris, Daniele Grandi, Ryan Tomich, Md Ferdous Alam, Mohammadmehdi Ataei, Hyunmin Cheong, et al. *Journal of Computing and Information Science in Engineering 25(2):021009*, 2025. *(Dataset)* - **Evaluating large language models for material selection** — Daniele Grandi, Yash Patawari Jain, Allin Groom, Brandon Cramer, Christopher McComb *Journal of Computing and Information Science in Engineering 25(2):021004*, 2025. *(LLM)* - **MSEval: A Dataset for Material Selection in Conceptual Design to Evaluate Algorithmic Models** — Yash Patawari Jain, Daniele Grandi, Allin Groom, Brandon Cramer, Christopher McComb *Journal of Mechanical Design 147(4)*, 2025. *(Dataset)* - **Elicitron: A Large Language Model Agent-Based Simulation Framework for Design Requirements Elicitation** — Mohammadmehdi Ataei, Hyunmin Cheong, Daniele Grandi, Ye Wang, Nigel Morris, Alexander Tessier *Journal of Computing and Information Science in Engineering 25(2)*, 2025. *(LLM)* - **A Domain Adaptation of Large Language Models for Classifying Mechanical Assembly Components** — Fatemeh Elhambakhsh, Daniele Grandi, Hyunwoong Ko *arXiv:2505.01627*, 2025. *(LLM)* [link](https://arxiv.org/abs/2505.01627) - **Do Large Language Models Produce Diverse Design Concepts? A Comparative Study with Human-Crowdsourced Solutions** — Kevin Ma, Daniele Grandi, Christopher McComb, Kosa Goucher-Lambert *Journal of Computing and Information Science in Engineering 25(2)*, 2025. *(LLM)* - **RECALL-MM: A Multimodal Dataset of Consumer Product Recalls for Risk Analysis using Computational Methods and Large Language Models** — Diana Bolanos, Mohammadmehdi Ataei, Daniele Grandi, Kosa Goucher-Lambert *arXiv preprint arXiv:2503.23213*, 2025. *(Dataset)* - **On the effectiveness of Large Language Models in the mechanical design domain** — Daniele Grandi, Fabian Riquelme *arXiv preprint arXiv:2505.01559*, 2025. *(LLM)* ### 2024 - **What’s in a Name? Evaluating Assembly-Part Semantic Knowledge in Language Models Through User-Provided Names in Computer Aided Design Files** — Peter Meltzer, Joseph G Lambourne, Daniele Grandi *Journal of Computing and Information Science in Engineering 24(1):011002*, 2024. *(LLM)* - **HG-CAD: hierarchical graph learning for material prediction and recommendation in computer-aided design** — Shijie Bian, Daniele Grandi, Tianyang Liu, Pradeep Kumar Jayaraman, Karl Willis, Elliot Sadler, et al. *Journal of Computing and Information Science in Engineering 24(1):011007*, 2024. *(Graph Neural Network)* - **Elicitron: An LLM agent-based simulation framework for design requirements elicitation** — Mohammadmehdi Ataei, Hyunmin Cheong, Daniele Grandi, Ye Wang, Nigel Morris, Alexander Tessier *arXiv preprint arXiv:2404.16045*, 2024. *(LLM)* - **Exploring the capabilities of large language models for generating diverse design solutions** — Kevin Ma, Daniele Grandi, Christopher McComb, Kosa Goucher-Lambert *arXiv preprint arXiv:2405.02345*, 2024. *(LLM)* - **DesignQA: Benchmarking Multimodal Large Language Models on Questions Grounded in Engineering Documentation** — Anna C Doris, Daniele Grandi, Ryan Tomich, Md Ferdous Alam, Hyunmin Cheong, Faez Ahmed *International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (American Society of Mechanical Engineers)*, 2024. *(Dataset)* - **Elicitron: A Framework for Simulating Design Requirements Elicitation Using Large Language Model Agents** — Mohammadmehdi Ataei, Hyunmin Cheong, Daniele Grandi, Ye Wang, Nigel Morris, Alexander Tessier *International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (American Society of Mechanical Engineers)*, 2024. *(LLM)* - **Material Selection Using Large Language Models** — Yash Patawari Jain, Daniele Grandi, Allin Groom, Brandon Cramer, Christopher McComb *International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (American Society of Mechanical Engineers)*, 2024. *(LLM)* ### 2023 - **Embedding Experiential Design Knowledge in Interactive Knowledge Graphs** — Ye Wang, Nicole Goridkov, Vivek Rao, Dixun Cui, Daniele Grandi, Kosa Goucher-Lambert *Journal of Mechanical Design 145(4):041412*, 2023. *(Knowledge Graph)* - **What's in a Name? Evaluating Assembly-Part Semantic Knowledge in Language Models through User-Provided Names in CAD Files** — Peter Meltzer, Joseph G Lambourne, Daniele Grandi *arXiv preprint arXiv:2304.14275*, 2023. *(LLM)* - **Conceptual design generation using large language models** — Kevin Ma, Daniele Grandi, Christopher McComb, Kosa Goucher-Lambert *International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (American Society of Mechanical Engineers)*, 2023. *(LLM)* - **HG-CAD: Hierarchical Graph Learning for Material Prediction and Recommendation in CAD** — Shijie Bian, Daniele Grandi, Tianyang Liu, Pradeep Kumar Jayaraman, Karl DD, Elliot Sadler Willis, et al. 2023. *(Graph Neural Networks)* ### 2022 - **Material prediction for design automation using graph representation learning** — Shijie Bian, Daniele Grandi, Kaveh Hassani, Elliot Sadler, Bodia Borijin, Axel Fernandes, et al. *International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (American Society of Mechanical Engineers)*, 2022. *(Graph Neural Network)* - **Classifying component function in product assemblies with graph neural networks** — Vincenzo Ferrero, Bryony DuPont, Kaveh Hassani, Daniele Grandi *Journal of Mechanical Design 144(2):021406*, 2022. *(Graph Neural Network)* - **A3d: Studying pretrained representations with programmable datasets** — Ye Wang, Norman Mu, Daniele Grandi, Nicolas Savva, Jacob Steinhardt *Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition*, 2022. *(Dataset)* - **Joinable: Learning bottom-up assembly of parametric cad joints** — Karl DD Willis, Pradeep Kumar Jayaraman, Hang Chu, Yunsheng Tian, Yifei Li, Daniele Grandi, et al. *Proceedings of the IEEE/CVF conference on computer vision and pattern recognition*, 2022. *(Machine Learning)* - **Capturing designers’ experiential knowledge in scalable representation systems: a case study of knowledge graphs for product teardowns** — Nicole Goridkov, Vivek Rao, Dixun Cui, Daniele Grandi, Ye Wang, Kosa Goucher-Lambert *International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (American Society of Mechanical Engineers)*, 2022. *(Knowledge Graph)* ### 2021 - **Understanding professional designers’ knowledge organization behavior: A case study in product teardowns** — Ye Wang, Daniele Grandi, Dixun Cui, Vivek Rao, Kosa Goucher-Lambert *International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (American Society of Mechanical Engineers)*, 2021. *(Knowledge Graph)* ### 2016 - **Embedded sensors and feedback loops for iterative improvement in design synthesis for additive manufacturing** — Mehdi Nourbakhsh, Nigel Morris, Michael Bergin, Francesco Iorio, Daniele Grandi *International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (American Society of Mechanical Engineers)*, 2016. *(Generative Design)* ## Patents - **2025** — *Filtering materials based on user intent capture using large language models.* Andrew John Harris, Daniele Grandi, Kendra Ann WANNAMAKER, Michael Chen, Allin Irving Groom (US Patent 12,393,573) - **2024** — *Macrostructure topology generation with disparate physical simulation for Computer Aided Design and Manufacturing.* Konara Mudiyanselage Kosala Bandara, Karl Darcy Daniel Willis, Andrew John Harris, Andriy Banadyha, Daniele Grandi, Adrian Adam Thomas Butscher, et al. (US Patent 11,947,334) - **2023** — *Conversion of geometry to boundary representation with facilitated editing for computer aided design and 2.5-axis subtractive manufacturing.* Karl Darcy Daniel Willis, Nigel Jed Wesley Morris, Andreas Linas Bastian, Adrian Adam Thomas Butscher, Daniele Grandi, Suguru Furuta, et al. (US Patent App. 17/945,008) - **2022** — *Conversion of geometry to boundary representation with facilitated editing for computer aided design and 2.5-axis subtractive manufacturing.* Karl Darcy Daniel Willis, Nigel Jed Wesley Morris, Andreas Linas Bastian, Adrian Adam Thomas Butscher, Daniele Grandi, Suguru Furuta, et al. (US Patent 11,455,435) ## Research Themes & Keywords - Data-driven design and design automation - Large Language Models (LLMs) for engineering design - Vision-Language Models (VLMs) for engineering documentation - Graph Neural Networks (GNNs) on CAD assemblies - Knowledge graphs for product teardowns and experiential design knowledge - Material selection and recommendation systems - Generative design and topology optimization - Additive manufacturing (polymer and metal) - Benchmarks and datasets for engineering AI (e.g., Fusion 360 Gallery, DesignQA, MSEval, RECALL-MM) - Agentic AI for requirements elicitation and conceptual design ## How to use this file This file is intentionally written as a single, self-contained Markdown document so it can be: 1. Placed at the root of the repo as `AGENTS.md` for AI coding/research agents that look for project-level context. 2. Downloaded from the website and pasted (or attached) into an LLM chat (e.g., ChatGPT, Claude, Gemini) to ask questions like: - *"Summarize Daniele's research on LLMs for engineering design."* - *"Which papers should I read first to understand his work on material selection?"* - *"List Daniele's collaborations with academic institutions."* - *"What patents has Daniele co-authored, and what are they about?"* For the latest publications, always cross-reference [Google Scholar](https://scholar.google.com/citations?user=X0qp478AAAAJ&hl=en).