Machine Learning Engineer - Humanoid Robotics

Overview

• NVIDIA is seeking exceptional machine learning engineers to join our world-class robotics initiatives focused on humanoid loco-manipulation.
• As part of the Isaac Loco-Manipulation team, you’ll collaborate with industry-leading experts, contribute to robotics foundation models including GR00T and Cosmos, and help define the future of humanoid robot capabilities.
• We are looking for strategic, ambitious, and creative individuals passionate about advancing the boundaries of robotics.This is demanding, cross-disciplinary work at the intersection of cutting-edge research and rigorous engineering.
• What you'll be doing: Collaborate with researchers and engineers to define and execute projects in humanoid robotics loco-manipulation and mobile manipulation areas.
• Contribute to the development and advancement of GR00T and Cosmos foundation models.
• Develop reference workflows with Isaac Lab and Newton for humanoid and mobile manipulation dexterous tasks.
• Advance technologies for robot learning and synthetic data generation using human videos.
• Design, implement, and deploy novel algorithms for humanoid robot locomotion and manipulation in both simulated and real-world environments.
• Transfer innovations into products, with deliverables including prototypes, open source software contributions, patents, and/or publications in top conferences and journals.
• Drive the full development lifecycle from model and algorithm design, with sim-to-real transfer, to rigorous on-robot validation and production deployment.
• Collaborate cross-functionally with teammates and partners to share best practices and advance shared goals.
• What we need to see: This role prioritizes candidates with proven execution bandwidth of applied research and engineering and a strong delivery track record on robotics platforms.
• PhD or Master’s degree in Robotics, Computer Science, or a related field (or equivalent experience).
• 3+ years of experience working on robotics software.
• Experience with deep learning frameworks such as PyTorch, JAX, or TensorFlow, and physics simulation tools like Isaac Sim/Lab or MuJoCo.
• Expertise in foundation models for robotics and 3D perception.
• Experience with sim-to-real and real-to-sim transfer in robotics.
• Deep knowledge of robot learning, including imitation and reinforcement learning.
• Hands-on experience of real robot testing, humanoid experience is preferred.
• Strong software engineering fundamentals, including proficiency in C++ and Python.
• Ways to stand out from the crowd: Experience learning from human video demonstrations or human-object reconstruction.
• Expertise in dexterous bimanual manipulation or whole-body control.
• Proven track record in robotics research, including publications in top conferences (e.g., RSS, ICRA, CoRL, NeurIPS, CVPR, ICLR).
• Demonstrated technical leadership experience.