Nuro is looking to improve its autonomous driving technology through the development of online and offline unstructured sensor calibration algorithms.
Requirements
- Hands-on experience in the research, development, and implementation of machine learning methods with sensor data (IMU, camera, lidar, radar, etc.).
- Experience with classical state estimation techniques (non-linear least-squares optimization, lie algebra).
- Deep understanding of ML fundamentals with hands-on experience in training and evaluating modern ML models.
- Strong Python skills with experience in deep learning frameworks, e.g., PyTorch, TensorFlow, or Jax.
- Deep understanding of 3D geometry and state estimation fundamentals.
- Proficiency in systems coding.
- Experience in building offline/online state estimation and/or calibration algorithms with camera, lidar, radar, IMU, etc.
Responsibilities
- Research and develop state-of-the-art state estimation and calibration algorithms combining classic robotics and modern ML techniques.
- Analyze and characterize the accuracy and performance of state estimation and calibration algorithms.
- Integrate state estimation and calibration pipelines into the autonomy system and analyze onboard performance and resource utilization.
- Work cross-functionally with other autonomy teams to accelerate the training of ML models and end-to-end performance evaluation.
- Answer critical questions about sensor data and autonomy performance.
Other
- One of: PhD in machine learning, computer science, electrical engineering, robotics, or related field, and 3+ years of industry experience, Masters and 4+ years of industry experience, or 5+ years of industry experience.
- Demonstrated research publications in top conferences (e.g. NeurIPS, ICLR, ICML, CVPR, RSS, CoRL, ICRA).
