Senior Computer Vision Engineer - Vllm

Senior Computer Vision Engineer - vLLM

XPENG is a leading smart technology company at the forefront of innovation, integrating advanced AI and autonomous driving technologies into its vehicles, including electric vehicles (EVs), electric vertical take-off and landing (eVTOL) aircraft, and robotics. With a strong focus on intelligent mobility, XPENG is dedicated to reshaping the future of transportation through cutting-edge R&D in AI, machine learning, and smart connectivity.

We are seeking a passionate and skilled Computer Vision Engineer to design and implement cutting-edge computer vision systems. Your work will focus on in-cabin scenarios, including, but not limited to: detection and classification of occupants and objects, understanding and analyzing human actions and behaviors, and perceiving in-cabin ambience.

Key Responsibilities

• Design multimodal (image/video/text) models using state-of-the-art machine learning and neural network algorithms.
• Create and curate training datasets; iteratively refine data based on model performance and project requirements.
• Implement and optimize distributed training frameworks to accelerate model development.
• Collaborate with deployment teams to enable efficient edge and on-device model deployment.
• Stay current with academic research and integrate novel algorithms into production workflows.
• Coordinate cross-functional efforts across teams and departments.

Minimum Requirements

• Master's or Ph.D. in Computer Science or a related field, with strong expertise in computer vision and machine learning. Open to new graduates.
• Hands-on experience in model development (CV/VL models) and algorithm optimization.
• Proficiency in PyTorch or TensorFlow, and experience with data preprocessing techniques.
• Strong collaboration and communication skills.
• Ability to read, interpret, and implement research papers effectively.

Preferred Qualifications

• Experience coordinating across multiple teams.
• Familiarity with large-scale model pretraining, quantization, or distributed training.
• Publications in top-tier conferences (e.g., CVPR, ICCV, NeurIPS) or contributions to open-source projects.
• Experience with edge device deployment or applications in autonomous driving.