Salary Range: 120000 to 165000 (Currency: USD) (Pay period: per-year-salary)

What you will do:

• Develop computer vision and machine learning algorithms/models.
• Implement and optimize models for deployment across a wide range of WeRide vehicles.
• Design and implement algorithms for sensor fusion, robust pose estimation and neural 3D reconstruction.
• Analyze autonomous driving simulation and road test data to identify and resolve motion planning issues.

Qualifications:

• MS/PhD degree in Robotics, Computer Science, Physics, Computer Vision, Machine Learning, Automation or equivalent practical experience, with an expected graduation date between December 2024 and June 2025.
• Proficient in C++ and/or Python with knowledge of its latest features.
• Strong understanding of machine learning approaches and algorithms, including but not limited to NLP, computer vision, reconstruction algorithms, image generation, or multi-modal models.
• Strong analytical and problem-solving skills.
• Excellent communication, and cross-functional team collaboration abilities.
• Passion for innovation in the autonomous vehicle industry.

Bonus Points:

• Published research presented at leading machine learning or robotics conferences such as NeurIPS, CVPR, ICML, ICLR, ICCV, ECCV, IROS, or ICRA.
• Proficient in machine learning frameworks, such as TensorFlow or PyTorch.
• Experience in open-source competitions or challenges related to autonomous driving.

Team Introductions:

• Perception Team:  
The Perception team is responsible for developing CV/ML algorithms to understand the surroudnings of ego vehicle in real time (obstacle detection, online mapping, scene understanding, etc.). Perception system takes inputs from multiple sensors across time, and outputs various obstacle-level and scene-level understandings for downstream systems (prediction, planning, etc.).
• Prediction Team:
The Prediction team liaises with the perception team upstream and the planning and control team downstream. We develop diverse deep learning models using perceptual information to forecast potential future behaviors of nearby obstacles. In scenarios lacking sufficient data, the prediction team generates predictions and supplements through analysis of scene features and logical reasoning.
• Planning and Control Team:
The main goal of the planning and control team is to find safe driving strategies in complex autonomous driving environments. We ensure safe, efficient navigation by designing algorithms for route planning and vehicle control to respond to dynamic conditions. Our work integrates sensor data and predictive models to make real-time decisions for smooth and reliable autonomous driving.
• Mapping and Localization Team:
The mapping and localization team is responsible for high-definition mapping and high-precision localization systems for our entire autonomous fleet. We provides down-stream modules, e.g. perception, prediction, planning and control, with accurate and real-time positioning as well as detailed geometric and semantic information of the surroundings, to help the autonomous vechile navigate the world. A variety of underlyiing technologies are employed to build the mapping and localization systems, including multi-sensor fusion, visual/lidar SLAM, 3D computer vision and deep learning.
• WeBoost Team:
The WeBoost team focuses on generating more realistic and diverse simulation environments based on extensive road test data for the training and evaluation of autonomous driving systems. This includes the Agent Planning & Execution Model, Generative Model, and 3D reconstruction model