Senior Perception Learning Engineer

Join Apptronik as a Senior Perception Learning Engineer, where you will lead the research and development of advanced perception systems for humanoid robots. Your work will focus on SLAM, visual-inertial odometry, world modeling, and learning-based perception. You will design and optimize deep learning models for real-time detection, tracking, segmentation, scene understanding, and state estimation. Additionally, you will integrate data from multiple modalities into unified world models and collaborate with various teams to shape Apptronik's perception and autonomy roadmap.

Conduire la recherche et le développement de systèmes de perception avancés pour les robots humanoïdes d'Apptronik.

Contributions to open-source robotics or vision software stacks

Responsibilities

• Concevoir et optimiser des modèles d'apprentissage profond pour la détection, le suivi, la segmentation, la compréhension de la scène et l'estimation d'état en temps réel.
• Intégrer des données provenant de plusieurs modalités (caméras, LiDAR, capteurs de profondeur, IMUs) dans des modèles du monde unifiés.
• 3- 5+ years building and shipping perception and/or SLAM systems in robotics or real-time vision applications
• Deep understanding of 3D geometry, camera models, and probabilistic estimation (EKF/UKF, factor graphs, SLAM, VIO)
• Strong background in SLAM, VIO, probabilistic state estimation, and deep learning for computer vision
• Experience deploying optimized perception or SLAM models on edge hardware (GPU/NPU/embedded platforms) under compute, latency, and thermal constraints
• Track record of shipping ML/Perception or SLAM systems from R&D into production robotics platforms

Requirements

• MS/PhD in Computer Science, Robotics, Computer Engineering, or related field
• Hands-on experience with modern AI frameworks (PyTorch, JAX, TensorFlow) and computer vision / multi-modal libraries such as OpenCV, Detectron2, YOLO, and foundation models for perception and language (e.g., SAM, CLIP, DINOv2, Flamingo)
• Proficiency in Python and modern C++, with strong software engineering fundamentals (version control, testing, CI/CD)
• Experience with humanoid robots, bipedal locomotion, and manipulation tasks
• Experience with modern SLAM frameworks (e.g., ORB-SLAM, VINS, Kimera, Cartographer) or learning-based SLAM systems
• Familiarity with real-time frameworks and middleware such as ROS 2, GStreamer, or zero-copy pipelines
• Expertise in model acceleration, quantization, or compression (TensorRT, ONNX Runtime)

Preferred

• Practical expertise in detection, segmentation, multi-object tracking, 3D perception, and learning-based mapping/localization
• Strong classical computer vision skills (geometry-based methods, feature extraction) complementing learning-based approaches
• Knowledge of synthetic data generation and domain adaptation techniques for training perception and SLAM models

Pay

USD 220,000 - 250,000