Researcher – 3D Vision and Autonomous Driving

About the role

We are seeking a researcher to independently contribute to cutting‑edge research and development in computer vision and autonomous driving. The role involves designing innovative solutions and advancing the state of the art in AI for autonomous systems.

Key responsibilities

• Architect and implement generative AI models for virtual scene generation, asset generation, and dynamic behavior simulation.
• Collaborate closely with cross‑functional teams (e.g., planning, perception) to integrate computer vision solutions into the broader autonomous driving system.
• Mentor and guide junior engineers and interns, fostering a collaborative and innovative team environment.
• Contribute to the development of our intellectual property portfolio through patent filings and publications.
• Stay abreast of the latest research and advancements in computer vision and machine learning, proactively identifying opportunities for innovation.
• Independently manage projects and deliver high‑quality results within established timelines.

Required profile

• Advanced degree (Ph.D./Master preferred) in Computer Science, Robotics, or a related field with a focus on computer vision and machine learning.
• Deep understanding of computer vision algorithms and techniques, including object detection, tracking, segmentation, and 3D reconstruction.
• Proven expertise in generative AI and its application to image, video and 3D generation (3DGS, Diffusion Model).
• Strong programming skills in Python and C++, with experience using deep learning frameworks (PyTorch, TensorFlow).
• Excellent problem‑solving and analytical skills, with the ability to tackle complex technical challenges.
• A strong publication record in top computer vision and machine learning conferences (e.g., ICCV, ECCV, CVPR, ICRA, NeurIPS).

Required skills

• Python
• C++
• PyTorch
• TensorFlow