AI Engineer - VLA Foundation Model, RIVR
Core
Develop multi-modal Vision-Language-Action (VLA) models and imitation learning algorithms to enable autonomous delivery robots to navigate and manipulate objects in real-world urban environments.
Role type
Senior IC machine-learning engineer (robotics, VLA models)
Builds
Autonomous delivery robots with enhanced navigation and manipulation skills
Domain
Robotics, Generative AI, Autonomous Systems
Deliverable
production ML models
Required skills
Vision-Language-Action (VLA) models, Imitation learning, Transformer architectures, Diffusion models, Robotics autonomy, Neural network deployment on edge hardware, Python (PyTorch)
Preferred skills
C++ (production-level), Team management, Top-tier conference publications
Technologies
PyTorch, Nvidia Jetson Thor, Transformers, Diffusion policies (via careerplan.io/jobs/10570666-ai-engineer-vla-foundation-model-rivr-at-amazon)
Responsibilities
Develop and implement VLA models and imitation learning algorithms; Design and refine algorithms for spatial reasoning and generalization; Streamline data collection and training workflows; Collaborate with reinforcement learning teams; Optimize networks for real-time edge deployment; Build and mentor a software engineering team; Provide strategic guidance to product managers and executives.
Seniority
Senior, hands-on IC with mentorship responsibilities