Cockpit AI Multimodal Architect
Core
Lead architecture design and technical implementation of the cockpit AI multimodal interaction system, integrating voice, vision, and gesture recognition for next-generation AI cockpit experiences.
Role type
Senior IC multimodal AI system architect
Builds
Automotive-grade multimodal interaction systems (voice, vision, gesture) and middleware
Domain
Automotive / AI Multimodal Interaction
Deliverable
production ML models | product features | infrastructure
Required skills
Multimodal perception fusion, AI decision engine design, ASR/NLU/CV/gesture recognition integration, edge-cloud collaborative interaction, technical roadmap planning
Preferred skills
On-vehicle large model adaptation, emotional interaction design, cross-modal context understanding
Technologies
Automatic Speech Recognition (ASR), Natural Language Understanding (NLU), Computer Vision (CV), Large Language Models (LLMs)
Responsibilities
Design hierarchical architecture for multimodal perception fusion, decision engine, and interaction execution; Evaluate and adapt AI algorithm engines for automotive use; Develop multimodal interaction middleware and standardized interfaces
Seniority
Senior, hands-on IC
