I pursue a Ph.D. in Architecture and a certificate in Statistics and Machine Learning at Princeton University. I joined the Form Finding Lab in 2022. My doctoral research work explores the application of automatic differentiation and graph-based machine learning to enable the design of safe, efficient, and expressive structures for buildings. I am broadly interested in developing new structural design methods and making them available to others as design tools.
My academic background intersects the fields of architecture, structural design, and computation. I hold a Master of Advanced Studies in Architecture and Digital Fabrication from ETH Zürich. The output of my master thesis was a computational method to generate rebar layouts aligned to principal stress directions on free-form, reinforced-concrete surfaces. Before that, I received a B.Sc. in Civil Engineering with Honors from Tec de Monterrey in Mexico and spent a term abroad at the National University of Singapore.
My professional experience spans both industry and academia. I worked for over three years at Bollinger+Grohmann in Germany where I was responsible for the structural design of geometrically complex sculptures and art installations. At the Block Research Group, I developed software that streamlined the engineering and fabrication of full-scale prototypes for the two rib-stiffened, funicular slabs now featured in the NEST HiLo unit. At Gramazio Kohler Research, and in collaboration with Autodesk, I contributed to the development and deployment of a deep reinforcement learning model that successfully overcame geometrical and material inaccuracies during the robotic assembly of architectural-scale timber structures. When not in front of a computer, I have led the construction of brick-and-mortar buildings using vernacular fabrication techniques in rural Southern Mexico.