Software Engineer, Robotics
Core
Build production software systems connecting data pipelines, simulation, training loops, and evaluation for Vision-Language-Action (VLA) foundation models to enable robot learning.
Role type
Senior IC software engineer (robotics & VLA systems)
Builds
VLA training integration layers, evaluation/benchmarking infrastructure, dataset management systems, sim-to-real transfer tooling, and annotation platform backends.
Domain
Robotics, Embodied AI, Machine Learning
Deliverable
production ML models
Required skills
Python, Linux, Docker, CUDA, cloud infrastructure, robot learning (imitation learning, behavior cloning, diffusion policies, RL), robotics simulation, robotics data formats/middleware
Preferred skills
VLA codebases (RT-2, Octo, OpenVLA, π0, GR00T), NVIDIA Omniverse/Replicator/Cosmos, sim-to-real transfer techniques, ML eval frameworks, open-source contributions
Technologies
LeRobot, Octo, OpenVLA, π0, Isaac Lab, Isaac Sim, GR00T-Mimic, OSMO, NVIDIA Isaac ecosystem, ROS/ROS2, URDF/USD, MCAP, HDF5, AWS/GCP
Responsibilities
Build VLA training integration layer (data loaders, format converters, preprocessing); Develop evaluation and benchmarking infrastructure (sim-based rollouts, success-rate tracking, automated reporting); Own dataset management (versioning, schema validation, metadata indexing); Implement sim-to-real transfer tooling; Build annotation platform backend systems; Integrate with NVIDIA Isaac ecosystem for synthetic data generation.
Seniority
Senior, hands-on IC
