Mid-Level Computer Vision & 3D Deep Learning Engineer

Responsibilities

• Research, prototype, and integrate new deep learning algorithms from recent literature (NeurIPS, CVPR, ICCV, ECCV) to improve 3D reconstruction quality
• Develop and maintain deep learning components for multi-view reconstruction, landmark detection, segmentation, inpainting, and view-consistent shape fitting
• Implement and tune custom training pipelines and loss functions, evaluating their impact on mesh and texture quality
• Design and run quantitative evaluation experiments using metrics such as reprojection error and surface-to-surface distance
• Export and deploy trained models for inference using tools like TorchScript/JIT or Triton Inference Server

Requirements

• 2–3 years of hands-on experience in computer vision and deep learning research or applied engineering
• Solid understanding of camera models, projective geometry, and multi-view geometry
• Proficiency in Python and PyTorch
• Ability to read and implement methods from academic papers
• Experience training and debugging neural networks end-to-end, including custom loss functions and training stability
• Fluent or proficient in English

Preferred Qualifications

• Experience with 3D vision techniques such as NeRFs, differentiable rendering, or SLAM
• Understanding of implicit surface representations like Signed Distance Functions (SDFs) or occupancy networks
• Familiarity with classical 3D fitting approaches, including statistical shape models and ICP
• Knowledge of libraries such as Open3D, PyTorch3D, or OpenCV
• Experience with experiment tracking tools like MLflow or W&B
• Experience deploying models to production using Docker
• Background in geometry, linear algebra, or computer graphics

About the Company

Crisalix develops advanced 3D technologies and AI-driven solutions for the medical and aesthetic industries, focusing on high-quality 3D reconstruction and visual simulation.