VLA for Physical AI (Talent pool)
Core
Building multimodal driving models that connect visual perception, scene context, and driving actions to enable robust autonomous driving behavior using VLA-style modeling approaches.
Role type
Senior IC machine-learning engineer (autonomous driving)
Builds
Production multimodal driving models for on-vehicle execution
Domain
Autonomous driving, visual perception, decision-making
Deliverable
production ML models
Required skills
multimodal modeling, visual perception, scene context understanding, driving action generation, VLA-style modeling, prior knowledge integration, production deployment, on-vehicle execution
Preferred skills
planning, decision-making, action generation
Technologies
VLA-style modeling frameworks
Responsibilities
Develop multimodal driving models connecting visual perception and scene context to driving actions; leverage VLA-style modeling for improved generalization; focus on production deployment and on-vehicle execution
Seniority
Senior, hands-on IC
