具身智能多模态交互产品专家-火山引擎
Core
Define and plan multi-modal interaction products (voice, vision, gesture, haptics, environmental sensing) for embodied intelligence scenarios like smart cars, robots, and smart homes.
Role type
Senior Product Expert, Embodied Intelligence Multi-modal Interaction
Builds
Embodied intelligence products with disruptive interaction experiences in smart cars, robots, and smart homes
Domain
Embodied Intelligence, AI, Robotics, Smart Mobility
Deliverable
product features
Required skills
Multi-modal interaction definition, multi-modal perception fusion, intent understanding, scenario-based decision making, product requirement documentation, UX/UI collaboration, algorithm-engineering collaboration, product delivery management, user research, data analysis
Preferred skills
Smart car cockpit experience, service robot experience, XR device experience, embodied intelligence knowledge, multi-modal large model knowledge, robotics technology knowledge
Technologies
Multi-modal large models, perception fusion, decision planning, natural language processing, task planning
Responsibilities
Analyze industry trends and customer needs to define interaction experiences; Lead definition of multi-modal interaction capabilities; Collaborate with UX/UI designers to create interaction prototypes; Collaborate with algorithm and engineering teams to integrate and optimize technologies; Ensure product delivery and iterate based on user feedback; Manage project milestones and mitigate risks.
Seniority
Senior, hands-on IC
