Mid-Level Computer Vision & 3D Deep Learning Engineer (AI)

TL;DR

Mid-Level Computer Vision & 3D Deep Learning Engineer (AI): Developing and deploying models for multi-view 2D to 3D reconstruction with an accent on 3D geometry and neural representations. Focus on implementing state-of-the-art deep learning algorithms, optimizing training pipelines, and integrating models into production-grade systems.

Location: Must be based in Barcelona, Spain

Company

hirify.global is a technology company specializing in advanced 3D reconstruction and computer vision solutions.

What you will do

• Research, prototype, and integrate new deep learning algorithms from recent literature (NeurIPS, CVPR, ICCV, ECCV).
• Develop deep learning components for multi-view reconstruction, landmark detection, segmentation, and inpainting.
• Implement and tune custom training pipelines and loss functions to improve mesh and texture quality.
• Design and run quantitative evaluation experiments using reprojection error and perceptual quality scores.
• Export and deploy trained models for inference using TorchScript/JIT and 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.
• Strong Python skills and proficiency with PyTorch (primary) and/or TensorFlow.
• Ability to read and implement methods from academic papers.
• English: Fluent or proficient proficiency required.
• Location: Based in Barcelona.

Nice to have

• Experience with NeRFs, differentiable rendering, SLAM, and implicit surface representations (SDFs, occupancy networks).
• Familiarity with libraries such as Open3D, PyTorch3D, or OpenCV.
• Knowledge of classical 3D fitting (PCA-based statistical shape models, ICP, mesh deformation).
• Experience with experiment tracking tools like MLflow or W&B.
• Proficiency with Docker and GPU performance tuning.