ML Engineer, Manipulation
Diligent Robotics4 months ago
Remote, United StatesMid Level
H1B sponsor
Responsibilities
- Develop learning-based manipulation models for end-to-end sensor-driven robot interaction.
- Build and maintain manipulation training pipelines using robot logs and teleoperation data, including action representations, augmentation, and distributed training.
- Design evaluation metrics, regression tests, and safety assessments for manipulation reliability and recovery behavior.
- Develop sim-to-real workflows with simulation environments, domain randomization, synthetic data, and failure-mode testing.
- Optimize and distill models for edge deployment while benchmarking latency, memory usage, and stability on target hardware.
- Integrate learned policies with control and safety systems and validate end-to-end performance on robots.
- Analyze field performance, identify failure modes, and drive improvements through data collection and targeted retraining.
Requirements
- Bachelor’s or master’s degree in Robotics, Computer Science, Electrical Engineering, or a related field; a PhD is a plus.
- At least 3 years of experience applying ML to robotics manipulation, visuomotor control, or sequence-to-sequence models.
- Strong proficiency in PyTorch and experience building reliable training and evaluation pipelines.
- Strong Python software engineering skills and ability to collaborate across ML and robotics teams.
- Preferred: experience with Vision-Language-Action models, behavior cloning, transformer or diffusion policies, and robotic control.
- Preferred: experience with sim-to-real training, Isaac Sim or MuJoCo, domain randomization, and synthetic data.
- Preferred: experience deploying ML models to edge hardware using ONNX or TensorRT, quantization, and performance profiling.
- Preferred: familiarity with safety-critical robotics integration and fallback or recovery behaviors.
Categories
ML EngineeringRobotics
About Diligent Robotics
Diligent Robotics builds and deploys Moxi, an autonomous mobile robot that performs hospital logistics—delivering supplies, lab samples, and equipment and handling routine errands so clinicians can focus on patient care. It sells robots and accompanying fleet-management software and services to hospitals and health systems, often operating them as a managed service. The company is headquartered in Austin, Texas, with deployments across U.S. hospitals supporting nursing and ancillary teams.