Robotics-Vision Research Engineer
Role details
Job location
Tech stack
Job description
- Integrate existing algorithms into a demonstrator using a real robot, including testing and optimization.
- Support researchers by identifying and testing algorithms from the literature.
- Implement algorithms in Python and maintain the current code repository. Prepare the code for releases. Liaise with colleagues globally for handover of the code.
- Create and support demonstrations using actual robots and prepare field tests. Ready to travel for field tests and evaluations in a real-world setting.
- Report findings at regular project meetings and prepare findings for publication.
Requirements
Do you have experience in Unity?, Do you have a Master's degree?, We are looking for a talented and curious individual that holds a Master level degree in robotics, engineering related field with practical robot experience and with a strong interest in research. The mission is to support the team of researchers in bringing algorithms to a service robot, test scenarios, analyze results, and propose new solutions. If you are a team player who thrives on responsibility, possesses strong robotics/vision skills, and has a deep understanding of vision and robotic foundation models, then you are the right person for this challenge., * MSc level in in computer science, engineering, physics or mathematics.
- Research experience and mindset.
- Hands-on mindset, practical and pragmatic for real-world problem solving.
- Self-motivation, be able to work under pressure, be able to manage multiple tasks effectively, and eager to learn
- Experience 1-3 years, * Experience in integrating perception and control algorithms into robotic systems for real-world testing and demonstrations
- Motion control algorithms with reinforcement/imitation learning
- Operating and debugging ROS1 based robots. Knowledge of ROS2 and integration of new sensors into an existing platform are a plus.
- Knowledge of the current state of the art in perception and robot navigation algorithms.
- Perception using computer vision methods and vision foundation models.
- Experience with physics simulation environments for training and evaluation of robotic policies.
- Foundation models (knowledge in large vision models, multi-modal models)
Technical Skills
- Programming languages: Python, C/C++
- Proficient in OpenCV, PyTorch, TorchVision
- Proficient in Linux environment, Docker, Git and HPC experience, preferable AWS and Azure
- Proficient in simulation environment, e.g., Gazebo, PyBullet, Genesis, NVIDIA Omniverse, Unity
- Experience with ROS1 and ROS2 frameworks
- Optional: experience in Gaussian Splatting and 3D rendering methods