Job Summary
This role focuses on the development and enhancement of Vision-Language-Action foundation models, aimed at empowering autonomous robotic systems to analyze visual data and perform intricate tasks. The position requires collaboration with various teams to seamlessly integrate perception systems and enhance models for deployment in edge AI environments.
Responsibilities
- Develop and refine foundational models for Vision-Language-Action applications.
- Enable robotic systems to effectively interpret visual inputs.
- Facilitate the execution of complex tasks by the robotic systems.
- Collaborate with diverse teams to integrate perception pipelines into existing systems.
- Optimize models for efficient performance in edge AI settings.
Qualifications
- Master’s degree or Ph.D. in a relevant technical discipline.
- 3 to 5 years of experience in multimodal AI, deep learning, or robotics.
- Proficient programming skills in Python.
- Hands-on experience with PyTorch and Transformer-based architectures.
