Senior AI Engineer - VLA Foundation Model

We are looking for a Senior AI Engineer to advance our global fleet of delivery robots, which continuously collect real‑world data for autonomous navigation and manipulation. The day‑to‑day work involves building multi‑modal Vision‑Language‑Action models that turn demonstrations, live sensor streams, and natural‑language commands into robot actions. These models aim to improve the robots' autonomy, navigation and manipulation capabilities, and you will also integrate large‑scale generalist models like Transformers into the VLA pipeline. The role requires deep expertise in VLA modeling, imitation learning, generative AI, and both supervised and self‑supervised learning methods. If you are passionate about pushing AI boundaries, you will help shape the future of intelligent robotics. What the role asks for: - Expertise in Vision‑Language‑Action (VLA) models - Experience with imitation learning - Proficiency in generative AI techniques - Strong knowledge of supervised learning algorithms - Strong knowledge of self‑supervised learning algorithms