Deep Learning Engineer, Perception

As a Deep Learning Engineer, you will apply your software engineering, deep learning, and 3D computer vision expertise to build perception capabilities for industrial robots. You will develop robust deep learning models for 3D computer vision tasks, including object detection, 6DoF pose estimation, and 3D reconstruction, and optimize algorithms for reliable grasping and manipulation in complex manufacturing environments. You will translate cutting-edge DL research into practical, production-grade solutions and contribute to core perception software components. You will collaborate with cross-functional teams to ensure robust deployment and maintainability, and you will work primarily with Python, C++, and modern DL frameworks such as PyTorch, TensorFlow, or JAX. Qualifications include a Master’s or PhD in CS/EE/Robotics or related fields and 1-3 years of experience in AI/ML/vision/robotics with a focus on DL, including transformer models; knowledge of deployment, optimization/quantization, and CUDA is a plus.