SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Apptronik is a Series B human-centered robotics company developing AI-powered humanoid robots (Apollo) to support humanity across manufacturing, logistics, healthcare, and beyond. As Senior Perception Learning Engineer, you will lead research and development of advanced perception systems that enable Apollo to understand and interact with complex human environments.
You will design and optimize deep learning models for real-time object detection, tracking, segmentation, pose estimation, and scene understanding. Your work spans the full perception stack: architecting scalable pipelines for training, evaluation, and deployment; integrating multi-sensor data (cameras, LiDAR, depth sensors, IMUs) into unified world models; and balancing research innovation with practical engineering to deliver deployable, high-performance systems.
Key responsibilities include leading perception pipeline design for humanoid locomotion and manipulation; developing multi-sensor fusion frameworks for dynamic human-centered environments; architecting data pipelines and inference frameworks; implementing performance profiling and regression testing for edge devices; collaborating with planning, control, and hardware teams on perception-to-action interfaces; guiding synthetic data integration (IsaacSim); and mentoring junior engineers.
You will work at the intersection of cutting-edge computer vision, robotics, and real-time systems. Required: MS/PhD in Computer Science, Robotics, or related field; 3-5+ years building and deploying perception systems for robotics or autonomous vehicles; strong deep learning expertise (detection, segmentation, tracking, 3D perception); proficiency with PyTorch, JAX, TensorFlow, and vision libraries (OpenCV, Detectron2, YOLO, foundation models); Python and modern C++; understanding of 3D geometry, camera models, and probabilistic estimation (SLAM, VIO); experience deploying optimized models on edge hardware; track record shipping ML systems to production robotics.
Preferred: humanoid robotics experience, classical computer vision skills, model acceleration expertise (TensorRT, ONNX), ROS 2 familiarity, synthetic data generation knowledge, open-source contributions.
