What you’ll be doing:
Develop the next features for our platform, such asperception-in-the-loopreinforcement learning, learning from demonstration via tele-operation, and multi-agent training.
Automate our workflows and scale them massively in the cloud.
Perform extensive benchmarking and profiling to ensure best-in-class system performance and scalability.
Collaborate with research and engineering teams all across NVIDIA, such as DEX and GEAR, to enable the next generation of humanoid robots.
Participate in code reviews, system design discussions, and contribute to internal and open-source software.
Engage with the robotics industrial and research communities.
What we need to see:
BS, MS, or PhD degree in Computer Science or relevant field (or equivalent experience).
Extensive experience in software development with Python and the deep-learning software stack (Pytorch, Tensorflow, Jax, etc.).
5+ years of experience in robotics and simulation workflows, including reinforcement learning, imitation learning, motion planning, and trajectory optimization.
Extensive experience with robotics simulation platforms, coupled with a deep understanding of physics-based simulation and expertise in tuning simulation parameters for accuracy and performance.
Strong foundation in software engineering best practices, including proficiency with Git, CI/CD workflows, docker, debugging methodologies, and comprehensive testing strategies; experience contributing to and maintaining open-source software projects.
Proficiency in using profiling and performance analysis tools to identify bottlenecks and optimize CPU and GPU workloads, ensuring efficient and scalable system performance.
Ways to stand out from the crowd:
Prior experience with Isaac Sim, Isaac Lab, Isaac Gym, or Mujoco.
You have already trained a robot in simulation and deployed the policy sim-to-real.
Publications in major AI and robotics conferences.
You will also be eligible for equity and .
משרות נוספות שיכולות לעניין אותך