🛠 Tech Stack

💼 About This Role

You'll develop and enhance deep learning models for 3D mesh estimation from images, prompts, and videos at a leading digital fashion company. Your work will directly impact the core algorithms powering CLO Virtual Fashion's 3D garment simulation platform. You'll collaborate on cutting-edge research in computer vision and graphics.

🎯 What You'll Do

• Develop 3D polygon mesh estimation models from images, prompts, or videos
• Build parametric CAD model estimation from diverse inputs
• Fine-tune and optimize large generative models like Stable Diffusion
• Create deep learning solutions for 3D avatar pose and shape estimation

📋 Requirements

• Master's or PhD in deep learning-based vision/graphics with 2+ years industry experience
• Project experience in Vision, 3D Deep Learning, or Generative models
• Proficiency in Python and PyTorch

✨ Nice to Have

• Experience with deep learning models on mesh or graph data
• Experience with generative models like Diffusion or StyleGAN
• Knowledge of computer graphics, geometry processing, or physically based rendering

📨 Hiring Process

Hiring process: document review, phone interview, first interview, second interview (paper seminar), third interview (plus reference check), compensation negotiation, final offer.