Machine Learning Engineer Intern - Auto-labeling

XPeng Motors is one of China’s leading smart electric vehicle (“EV”) companies. We design, develop, manufacture and market smart EVs that are seamlessly integrated with advanced Internet, AI and autonomous driving technologies. We are committed to in-house R&D and intelligent manufacturing to create a better mobility experience for our customers. We strive to transform smart electric vehicles with technology and data, shaping the mobility experience of the future.

We are looking for a full-time machine learning intern who could ideally intern for 6 months +, with strong enthusiasm towards 3D scene reconstruction and understanding.

Our mission is to solve the autonomous driving problem. You will work with a team of machine learning researchers to build AI software systems, learn about deep learning algorithms, and use your technical skills to advance autonomous driving.

Job Responsibilities:

• Develop algorithms for industry-level 3D reconstruction with massive data from surrounding cameras and LiDAR to facilitate self-driving autolabelling.
• Train large vision models to interpret reconstructed 3D scenes to pre-label multiple perception tasks including detection, segmentation and tracking.
• Work closely with upstream and downstream teams to deploy and maintain efficient auto-labelling pipelines to continuously generate ground truth.
• Explore new techniques and publications to address challenging problems in production.

Minimum Skill Requirements:

• PhD or Master in computer science, electrical engineering, robotics, or other related fields.
• Familiar with geometry-based 3D reconstruction tools/methods such as SfM, MVS, Colmap. Background in computer graphics is a plus.
• Familiar with learning-based 3D reconstruction methods such as NERF, 3DGS, differentiable rendering. Experience in generative models such as GAN, diffusion model is a plus.
• Write clean and efficient code in Python. C++ is a plus.
• Master at least one deep learning framework such as TensorFlow, PyTorch. Experience in large-scale distributed training is a plus.

What do we provide:

• A fun, supportive and engaging environment
• Opportunity to make significant impact on transportation revolution by the means of advancing autonomous driving
• Opportunity to work on cutting edge technologies with the top talent in the field
• Competitive compensation package
• Snacks, lunches, and fun activities

We are an Equal Opportunity Employer. It is our policy to provide equal employment opportunities to all qualified persons without regard to race, age, color, sex, sexual orientation, religion, national origin, disability, veteran status or marital status or any other prescribed category set forth in federal or state regulations.