NVIDIA accelerates robot development through Isaac solutions, GR00T, and Cosmos. We are looking for a robot learning and simulation expert to join the NVIDIA Japan Solution Architect team to support local robotics partners and customers. As a Solution Architect Intern, you will collaborate with Japan-based teams to help customers solve data preparation issues using Isaac and Cosmos. Your work will help robotics customers adopt robot learning for their specific use cases.
What you'll be doing:
- You will set up data augmentation pipelines in Isaac Sim/Lab and Cosmos.
- Your task is to analyze and identify how synthetic data improves VLA performance and verify how different types of domain randomization contribute to the generalizability of VLA and world models.
What we need to see:
- Pursuing BS, MS, or PhD. experience with robotics learning and robot simulation.
- Strong academic background in Computer or Electrical Engineering, Computer Science, or related degree
- Experience in using robotics simulation tools: Isaac Sim or Mujoco
- Deep knowhow and experience in robotics policy training for locomotion or manipulation
- Strong experience in robotics policy evaluation in simulation and real environment
- Strong experience with Python, Container, and Linux
- Excellent communication and planning skills, while being self-motivated with a focus on execution and quality
Ways to stand out from the crowd:
- Background in robotics simulation and robotics learning
- Strong background and rich project experience in policy deployment sim2sim and sim2real gaps analytics and mitigation results