- Zürich, Zürich, Switzerland
- On-site
- Full-time · Senior
- 3+ years
Develop multi-modal models (VLA, imitation learning, generative AI) to enable robots to autonomously generate actions from demonstrations, real-time sensor data, and natural language commands.
Responsibilities
- Develop and implement cutting-edge Vision-Language-Action (VLA) models, generalist robot transformers, and imitation learning algorithms (e.g., diffusion policies) to enable robots to autonomously execute complex tasks.
- Design, test, and refine your algorithms to meet the demands of complex real-world autonomy and navigation tasks, with a focus on spatial reasoning and generalization.
- Streamline the data collection and training workflow to efficiently expand model capabilities with new tasks and data sources.
- Collaborate with the reinforcement learning team to innovate methods that leverage both simulated and real-world data.
- Optimize and distill networks for real-time deployment on the edge (e.g. Nvidia Jetson Thor).
Requirements
- Master’s degree or higher in a relevant field such as Engineering, Robotics, or Machine Learning
- Nice to have: PhD degree in Robotics, Engineering, Computer Science, Machine Learning
- Nice to have: Publications at top-tier conferences
- Nice to have: Managing a software team
- Nice to have: C++