AI Spatial Vision Engineer

Perception We are building next-generation Spatial AI systems that enable robots and intelligent machines to understand, navigate, and interact with the physical world in real time. We are seeking a highly talented Spatial Vision Intelligence Engineer to develop advanced 3D perception, computer vision, and spatial reasoning technologies for autonomous robotics and industrial AI systems. This role is ideal for engineers passionate about computer vision, embodied AI, spatial intelligence, and real-world AI deployment. About the Role As a Spatial Vision Intelligence Engineer, you will design and develop AI perception systems that allow robots to perceive and understand complex environments using cameras, LiDAR, depth sensors, and multimodal spatial data. You will work on cutting-edge technologies involving: Real-time 3D scene understanding Spatial reasoning and mapping Visual localization and perception On-device AI inference Industrial robotics and autonomous systems ResponsibilitiesSpatial AI & 3D Vision Develop real-time 3D perception and spatial intelligence systems Design computer vision pipelines for autonomous robotics Build scene understanding, object tracking, and environmental mapping technologies Develop spatial reasoning algorithms for robot decision-making Implement multimodal perception systems using RGB, depth, LiDAR, and sensor fusion AI & Deep Learning Train and deploy deep learning models for vision intelligence Develop object detection, segmentation, tracking, and 3D reconstruction models Optimize AI inference pipelines for edge/on-device deployment Work with multimodal and embodied AI architectures Robotics & Autonomous Systems Integrate perception systems into robotics platforms Develop visual localization and SLAM systems Support robot navigation and autonomous operation Build simulation and digital twin environments for AI validation Engineering & Deployment Develop scalable Linux-based AI systems Optimize GPU and edge computing performance Collaborate with robotics, software, and hardware teams Deploy and validate systems in real industrial environments Required Qualifications Bachelor’s or Master’s degree in Computer Vision, Robotics, AI, Computer Science, or related fields Strong programming skills in Python and/or C++ Experience with computer vision and deep learning frameworks Experience with real-time vision processing systems Strong understanding of Linux environments Experience with: PyTorch OpenCV ROS/ROS2 Knowledge of 3D geometry, camera systems, and spatial computing Strong analytical and problem-solving skills Preferred Qualifications Experience with SLAM, visual localization, or spatial mapping Experience with LiDAR and point cloud processing Experience with NVIDIA CUDA, TensorRT, or GPU optimization Familiarity with Isaac Sim, Gazebo, or simulation environments Experience with edge AI and embedded systems Experience building autonomous robotics systems Publications, patents, or open-source contributions in vision AI or robotics Tech Stack Python / C++ ROS2 PyTorch OpenCV CUDA / TensorRT LiDAR / Depth Cameras Linux / Docker Edge AI Spatial AI / 3D Vision Isaac Sim / Gazebo Why Join Us? Work on cutting-edge Spatial AI and robotics technologies Build real-world embodied AI systems Opportunity to solve large-scale industrial automation challenges Access advanced GPU and robotics development infrastructure Fast-moving and highly technical engineering culture Opportunity to shape the future of intelligent autonomous systems Ideal Candidate We are looking for engineers who: Are passionate about spatial intelligence and embodied AI Love solving complex perception and autonomy problems Enjoy building AI systems that interact with the physical world Thrive in fast-paced startup environments Want to deploy real AI into real industrial applications

Design and develop AI perception systems for robots to understand complex environments using multimodal spatial data. Implement real-time 3D scene understanding, object tracking, and visual localization for industrial robotics.

Requires a degree in Computer Vision, Robotics, or AI with strong proficiency in Python, C++, and deep learning frameworks. Experience with ROS2, OpenCV, and 3D geometry is essential for developing on-device AI inference.

• DockerSouhaitée
• LinuxSouhaitée
• C++Souhaitée
• PythonSouhaitée

Relevées dans la description du poste. Confirmez les exigences importantes ci-dessus.

• Python
• C++
• PyTorch
• OpenCV
• ROS2
• CUDA
• TensorRT
• 3D Perception
• SLAM
• LiDAR
• Computer Vision
• Deep Learning
• Spatial AI
• Linux
• Docker
• Edge AI

• Engineering
• Technology
• Software
• Science & Research
• Manufacturing

Formation minimale

Baccalauréat

Expérience minimale

0+ ans

Postuler avant le

22 sept. 2026

Langue de l’offre

anglais

Heures de travail

40 heures par semaine

Niveau d’expérience

Entry level

Mode de candidature

La candidature directe est offerte