AI Intern – Scenario Analysis

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.

 

Our team is working on the deployment of next-generation Vision-Language-Action (VLA) models for global autonomous driving products, and we’re looking for an intern to support data analysis, vector search, scenario classification, and long-tail scenario mining.

 

This role will focus on helping us identify and understand global region-specific driving scenarios, especially long-tail cases that matter for real-world model performance and deployment.

• Analyze large-scale global driving data to identify long-tail and region-specific scenarios.
• Build workflows for vector search / semantic retrieval over scenario-related data.
• Apply ML and LLM-based methods for scenario classification, clustering, and tagging.
• Use embedding models, prompt engineering, and RAG-style pipelines to organize unstructured data and surface useful patterns.
• Support data mining, data cleaning, and scenario curation for VLA model improvement.
• Generate analyses, dashboards, and summaries to help the team understand failure cases and regional data gaps.

• Strong skills in Python, SQL, and data analysis.
• Experience with machine learning pipelines, clustering, classification, or unsupervised learning.
• Familiarity with embedding models, vector search, semantic retrieval, RAG, or prompt engineering.
• Strong analytical thinking and comfort working with large datasets.
• Interest in autonomous driving, multimodal ML, embodied AI, or VLA model.