Senior Perception Learning Engineer

Apptronik • Sunnyvale, CA

1d

About The Position

Apptronik is seeking a Senior Perception Learning Engineer to research, develop, and deploy perception systems for its humanoid robot, Apollo. The role focuses on SLAM, visual-inertial odometry, world modeling, learning-based perception, object detection, and multi-sensor fusion, supporting robust autonomy in real-world human environments. The engineer will design and optimize deep learning models and integrate camera, LiDAR, depth-sensor, and IMU data into unified world models for navigation, manipulation, safety, and human-robot interaction. The position balances research innovation with practical engineering to deliver high-performance, deployable perception and SLAM systems, while collaborating across reinforcement learning, platform software, systems, planning, control, and hardware teams. The work will contribute to Apptronik’s perception and autonomy roadmap and the safe operation of humanoid robots in dynamic environments.

Requirements

• MS or PhD in Computer Science, Robotics, Computer Engineering, or a related field.
• 3–5+ years building and shipping perception and/or SLAM systems in robotics or real-time vision applications.
• Strong background in SLAM, visual-inertial odometry, probabilistic state estimation, and deep learning for computer vision.
• Practical expertise in detection, segmentation, multi-object tracking, 3D perception, and learning-based mapping or localization.
• Hands-on experience with AI frameworks such as PyTorch, JAX, or TensorFlow, and computer vision or multimodal libraries such as OpenCV, Detectron2, YOLO, and perception or language foundation models such as SAM, CLIP, DINOv2, or Flamingo.
• Proficiency in Python and modern C++, with software engineering fundamentals including version control, testing, and CI/CD.
• Deep understanding of 3D geometry, camera models, and probabilistic estimation methods such as EKF/UKF, factor graphs, SLAM, and VIO.
• Experience deploying optimized perception or SLAM models on edge hardware, such as GPU, NPU, or embedded platforms, under compute, latency, and thermal constraints.
• Track record of shipping ML/perception or SLAM systems from R&D into production robotics platforms.

Nice To Haves

• Experience with humanoid robots, bipedal locomotion, and manipulation tasks.
• Experience with modern SLAM frameworks such as ORB-SLAM, VINS, Kimera, or Cartographer, or learning-based SLAM systems.
• Strong classical computer vision skills, including geometry-based methods and feature extraction, complementing learning-based approaches.
• Expertise in model acceleration, quantization, or compression, including TensorRT or ONNX Runtime.
• Familiarity with real-time frameworks and middleware such as ROS 2, GStreamer, or zero-copy pipelines.
• Knowledge of synthetic data generation and domain adaptation techniques for training perception and SLAM models.
• Contributions to open-source robotics or vision software stacks.

Responsibilities

• Design, develop, and optimize perception and SLAM pipelines for humanoid robots, including visual-inertial odometry, mapping, localization, object detection, tracking, segmentation, pose estimation, and scene understanding.
• Develop multi-sensor fusion frameworks integrating cameras, LiDAR, depth sensors, and IMUs for real-time state estimation and mapping in dynamic human-centered environments.
• Contribute to scalable data pipelines, training infrastructure, and inference frameworks for model development, evaluation, and deployment.
• Research and deploy learning-based models for SLAM, 3D scene understanding, and perception, optimized for humanoid locomotion, manipulation, and human-robot interaction.
• Implement performance profiling, regression testing, and telemetry systems to meet latency, accuracy, and reliability requirements on edge devices.
• Collaborate with planning, control, and hardware teams to define perception-to-action interfaces compatible with real-time locomotion and manipulation pipelines.
• Guide integration of synthetic data, including data from simulation frameworks such as IsaacSim, with real-world datasets to improve model generalization and robustness.
• Contribute to best practices in code quality, model versioning, reproducibility, and deployment.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior