Translate open-ended, real-world problems into well-defined machine learning problems
Develop and implement computer vision algorithms for object detection and semantic environment perception on offroad terrain
Collaborate with the robotics team to integrate the computer vision algorithms into the robot navigation stack
Optimize computer vision algorithms for real-time processing on low-power embedded systems
Conduct testing and validation of computer vision algorithms in various outdoor environments
Stay up-to-date with latest advancements in computer vision technology and incorporate them into Angsa Robotics' products
Your profile
2+ years of experience in computer vision and perceptual tasks,
including but not limited to 3D perception, multi-class object detection, and image segmentation using deep learning frameworks such as PyTorch
Experience with 3D perception and point cloud processing using libraries such as Open3D or PCL
Hands-on experience with embedded GPU hardware, CUDA and TensorRT
Excellent programming skills in Python
Experience with ROS (Robot Operating System) and robot control is a plus
Why us? ? A shaping role in a an emerging robot company - We are moving fast and you will learn a lot ? A creative, passionate and international team with flat hierarchies ? We support sports & sustainable mobility: 9€ Ticket + significant support for Urban Sports Club ? 30 paid vacation days to recharge ? Startup Vibe: Regular team events, flexible working hours & comfortable office About us Removal of small trash on grass and gravel is a painful manual process, as conventional cleaning machines cannot be used there. Angsa develops an autonomous robot, which detects even small trash items using artificial intelligence. The detected objects are then removed in a targeted manner, preserving the grass and insects. The autonomous robot enables festival organizers or parc administrations to save money and keep their areas clean, while increasing the cleaning speed and quality.