Computer Vision Engineer

One of our clients, a fast-growing deep-tech startup at the forefront of autonomous robotics, is looking to hire a Computer Vision Engineer with a strong focus on Deep Learning. This innovative company develops production-grade robotic systems that combine artificial intelligence, computer vision, and advanced robotics to transform the way large-scale infrastructure environments are inspected and maintained. Their solutions operate autonomously in complex 3D environments and are already deployed in real-world settings.

About the Role

This position is centered around the development and deployment of cutting-edge deep learning models for robotic perception. You will work at the intersection of research and engineering, designing models that help robotic systems understand and interact with their environments in real time. The role demands both a strong theoretical background and hands-on experience in building robust, scalable neural models for embedded deployment.

Responsibilities

• Design and implement deep learning models for object detection, semantic and instance segmentation, 3D reconstruction, and scene understanding.
• Develop learning-based solutions for depth and pose estimation, multi-view geometry, and 3D data processing (e.g., point clouds, voxel grids, meshes).
• Work with sensor data from LiDAR, stereo/RGB-D cameras, IMUs, and GNSS systems.
• Optimize models for real-time performance on embedded and robotic hardware.
• Develop and maintain training, evaluation, and experimentation pipelines for large-scale datasets.
• Participate in simulations, offline experiments, and field tests to evaluate and iterate on model performance.
• Collaborate with cross-functional teams including robotics, control systems, and hardware integration.

Requirements

• B.Sc. or M.Sc. in Computer Science, Electrical/Computer Engineering, Applied Mathematics, or a related field (Ph.D. is a plus).
• Proven experience in Deep Learning applied to Computer Vision tasks.
• Strong background in 3D perception techniques including depth estimation, pose estimation, SLAM, or 3D reconstruction.
• Hands-on experience working with 3D data formats such as Point Clouds, Meshes, or Neural Radiance Fields (NeRF).
• Proficiency in Python and frameworks such as PyTorch or TensorFlow; experience with OpenCV and PCL is an advantage.
• Familiarity with embedded systems and real-world deployment of neural networks.
• Ability to translate research concepts into robust, real-time production systems.