[Internship] Machine Learning 3D Computer Vision Engineer - 3D Gaussian Splatting (3DGS)

Role overview

Responsibilities

• check_circle <strong>Pipeline Automation:</strong> Design and automate the end-to-end data processing workflow, transforming raw multi-view video/image sequences from our cameras rig into finalized PyTorch-trained 4D Gaussian Splat assets via structure-from-motion (Colmap/SfM).
• check_circle <strong>SOTA Implementation:</strong> Research, integrate, and test recent State-of-the-Art papers to enhance visual fidelity, eliminate floating artifacts, and improve the structural accuracy of dynamic 4D volumetric scenes.
• check_circle <strong>Model Optimization &amp; Benchmarking:</strong> Profile training times and VRAM footprints. Implement compression, pruning, or quantization techniques to reduce file sizes, preparing the assets for mobile XR deployment constraints.

Basic qualifications

• <strong>Education:</strong> M.S. or Master 2 student in Computer Science, Data Science, or Robotics, specializing in <strong>Machine Learning, Deep Learning, or 3D Computer Vision</strong>.
• <strong>Technical Core:</strong> Strong proficiency with <strong>PyTorch</strong> and Python data science ecosystems. Solid foundational understanding of <strong>3D Computer Vision</strong> (camera matrices, stereo geometry, SfM/Colmap, NeRF, or Gaussian Splatting concepts).
• <strong>Bonus</strong> : Experience writing or modifying custom <strong>CUDA kernels</strong> or Vulkan Compute Shader
• <strong>Profile:</strong> High autonomy, self-learner, and deeply curious about the intersection of AI and real-time graphics.

Benefits

• check_circle Duration: 3 to 6 months. Starting Date: Automn
• check_circle Agreement: internship agreement needed with school or Erasmus+ agreement
• check_circle Compensation: ~661€ (31.50€ / day) + transport allowance
• check_circle Location: <strong>Bordeaux</strong> Center (startup coworking space)