Spawn Out Loud!
Spawn Out Loud!
Transformer model for text to 3d form generation
Embedded Files
3Ts model for designers
3Ts model for designers
DiT model for Sketch to 3d form generation
Graph out Loud!
Graph out Loud!
A Grasshopper GPT Action for parametric modelling with natural language.
(Under development)
Nexus Events
Nexus Events
NPC trained with RL for a game based on chain reaction
Ugly design
Ugly design
Image based Diffusion model for Residential floor plan generation
Tweak Ai
Tweak Ai
A GAN model to predict the buildable volume with a given context
Cybernetic Flappy bird
Cybernetic Flappy bird
A cybernetic model that allows us to play flappy bird with a volume controller
IN and OUT
IN and OUT
A Brick construction simulator with motion capture
At a Stretch!
At a Stretch!
Robotic path planning for 3d painting
(Under development)
Housefull
Housefull
An Ambient way of perceiving domestic data
Flood Prediction GAN
Flood Prediction GAN
A GAN model for flood prediction with a given context
Water cycle Simulation
Water cycle Simulation
A Dynamic mathematical model for global water cycle simulation
CAD Translator
CAD Translator
A LLM model to translate the cad construction drawings
Generative Parking
Generative Parking
A parametric tool that generates open parking layouts based on the given context
Spider
Spider
A Parametric grasshopper plugin that aids designers to analyze , visualize data and generate urban layouts with Rhino-Grasshopper
Stories of likes, tweets, and ideas
Stories of likes, tweets, and ideas
An algorithmic form generation for an office space
Beacon
Beacon
An algorithmic form generation for a tiny library
Advenir
Advenir
An algorithmic form generation for a skiing resort
Xerophyte
Xerophyte
An algorithmic form generation for an urban farm
Game Layout generation
Game Layout generation
An algorithmic generation of game layouts
Crawler
Crawler
3d Printed pen stand based on crawling agents
Space for pennies
Space for pennies
3d Printed Piggy bank
I’m a Generative AI researcher and design technologist working where machine learning meets spatial reasoning and human creativity. I build end-to-end systems—ML pipelines, model training, and intuitive interfaces—that turn complex planning and design problems into elegant, scalable tools. My practice spans LLM- and diffusion-driven co-pilots, reinforcement-learning agents, 3d generative models and multimodal workflows that connect geometry, simulation, and evaluation.
I care as much about usefulness as I do about novelty: human-in-the-loop feedback, custom evaluators, clear metrics, and reproducible experiments are baked into my process. I’m equally comfortable prototyping inside design toolchains and production-ready services, bridging computational design environments with modern ML stacks.
At Carnegie Mellon University and Studio.Compute, I’ve led cross-disciplinary teams, mentored emerging researchers, and delivered interactive tools for automation, decision support, and immersive XR/VR. Whether the brief involves augmenting creativity, spatial planning, or 3D generation workflows, my goal is the same: amplify designers’ judgment and accelerate high-quality outcomes. This portfolio documents that journey—and my commitment to expanding what’s possible with generative AI.
-Karthick Raja BG
+1(412)-689-6346 | karthickrajaforjobs@gmail.com | LinkedIn | CV
Page updated
Google Sites
Report abuse