Topic: teleoperation

Lead evaluation frameworks and data-collection protocols for robot capabilities. Define tasks, benchmarks and success criteria; stress-test policies against real-world cases; and turn observed failure modes into targeted training data. Build teleoperation workflows and operator interfaces, integrate logging and data pipelines with engineering teams, and lead projects through deployment while mentoring colleagues. The role connects robotics, machine learning and human-in-the-loop systems in New York. Advertised base pay is USD 172,400–223,400, with additional compensation and benefits. The empl

Nikita Rudin discusses reinforcement learning for robot locomotion and the difficulties of transferring policies from simulation to physical robots. Topics include visual inputs, real-world data for improving simulators, imitation learning and teleoperation, hierarchical control, and trade-offs between modular and end-to-end approaches for autonomous robots.