ML Engineer, Manipulation
Core
Develop and deploy learning-based manipulation systems enabling mobile robots to interact reliably with the physical world in dynamic human environments.
Role type
Senior IC machine-learning engineer (robotic manipulation)
Builds
Perception-to-action models, training datasets, evaluation tooling, and deployment pipelines for service robots
Domain
Robotics, AI, Physical Interaction
Deliverable
production ML models
Required skills
Learning-based manipulation, visuomotor control, sequential-to-sequence models, PyTorch, Python, distributed training, sim-to-real workflows, edge deployment optimization
Preferred skills
Vision-Language-Action (VLA) models, behavior cloning, transformer/diffusion policies, Isaac Sim/Mujoco, domain randomization, ONNX/TensorRT, safety-critical robotics integration
Technologies
PyTorch, Python, ONNX, TensorRT, Isaac Sim, Mujoco
Responsibilities
Develop end-to-end sensor-driven manipulation models; build and maintain training pipelines including dataset creation and augmentation; design evaluation metrics and regression tests; develop sim-to-real workflows with domain randomization; optimize and distill models for edge deployment; partner with AI platform teams to integrate policies with control systems; analyze field performance and drive iterative improvements
Seniority
Senior, hands-on IC
