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

Role overview

Responsibilities

• check_circle 4DGS Model Enhancement: Upgrade our polynomial-based 4DGS model by incorporating advanced temporal representations and compression techniques to improve scene fidelity and support longer sequences. Explore alternative representation (e.g. using video codecs)
• check_circle 3DGS & Runtime Optimization: Overhaul our 3DGS model and training pipeline to boost client-side FPS (e.g. eliminating non-contributing splats)
• check_circle 4DGS Generative Modeling: Benchmark and research SOTA 3DGS/4DGS world models capable of reconstructing 4DGS from from monocular video

Basic qualifications

• Education: M.S. or Master 2 student in Computer Science, Data Science, or Robotics, specializing in Machine Learning, Deep Learning, or 3D Computer Vision.
• Technical Core: Strong proficiency with PyTorch and Python data science ecosystems. Solid foundational understanding of 3D Computer Vision (camera matrices, stereo geometry, SfM/Colmap, NeRF, or Gaussian Splatting concepts).
• Bonus: Experience in OpenGL / Vulkan and reading CUDA kernel
• Profile: High autonomy, self-learner, and deeply curious about the intersection of AI and real-time graphics and eager to leverage agentic tools (e.g. Claude Code)

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: Bordeaux Center (startup coworking space)