VLA算法工程师/专家_XC
Core
Develop and deploy Vision-Language-Action (VLA) models for autonomous driving and embodied intelligence, focusing on multimodal understanding, instruction decomposition, and policy prediction.
Role type
Senior IC machine-learning engineer (VLA/Embodied AI)
Builds
High-performance VLA models capable of mass production, offline training frameworks, and real-time online inference systems.
Domain
Autonomous driving / Embodied intelligence
Deliverable
production ML models
Required skills
Multimodal understanding, instruction decomposition, policy prediction, diffusion models, Vision-Language Models (VLM), target detection, graph neural networks, NLP, large language models, C/C++, Python, parallel programming, code optimization, large-scale data processing
Preferred skills
Autonomous driving or embodied intelligence project experience, ACM competition experience, top-tier conference publications (CVPR/ICCV/ECCV/ICML/NeurIPS), top-tier journal publications (TPAMI/IJCV/TIP), actual engineering project experience
Technologies
Diffusion, VLM, C/C++, Python
