Key Responsibilities

• Conduct research to advance the state-of-the-art in Neural Radiance Fields (NeRF) and neural scene understanding for dynamic environments.
• Implement and optimize real-time algorithms for 3D scene reconstruction, rendering, and understanding in a dynamic context (e.g., moving objects, evolving environments).
• Develop methods to integrate dynamic scene updates into the NeRF framework while maintaining high performance and visual fidelity.
• Experiment with and enhance neural network architectures for real-time 3D vision applications.
• Performance Analysis: Analyze the performance of multi-modal models and propose improvements, such as model fine-tuning or optimizing for real-time applications.
• Documentation & Reporting: Write technical reports, document experimental results, and present findings to the team.

Minimum Qualifications

• Currently pursuing or recently completed a PhD degree in Computer Science, Artificial Intelligence, Robotics, or a related field.
• Extensive research background in computer science, deep learning, and 3D Computer vision.
• Strong programming skills in Python, with experience in machine learning libraries such as PyTorch, TensorFlow or similar and familiarity with 3D vision libraries (e.g., Open3D, PCL, etc.).
• Knowledge of neural rendering techniques, scene reconstruction, and techniques for handling dynamic environments.
• Proficiency in programming languages such as Python, C++, or similar, with strong coding practices.