Runs the team day to day
In-house, owns the opening
Joined the team recently
From your own Gmail and LinkedIn.
About the role
This is a remote machine learning engineering role in the United States focused on robotic manipulation, for engineers with at least three years of hands-on ML experience. You would build learning-based systems that let mobile robots handle physical tasks reliably in busy, human-filled spaces. The employer builds AI for service robots that work alongside people, and this role covers models, data pipelines, evaluation, and deployment to robot hardware.
What you’ll do
- Develop learning-based models that take sensor input through to robot actions such as reaching and motion generation.
- Build manipulation training pipelines covering dataset creation from robot logs and teleoperation, action representations, augmentation, and distributed training.
- Design evaluation metrics and regression tests for reliability, recovery behavior, and safety on real robots.
- Create sim-to-real workflows using simulation, domain randomization, and failure-mode testing.
- Optimize and distill models for edge hardware, benchmarking latency, memory use, and stability on target devices.
- Work with the AI platform team to connect policies to control and safety systems and validate them on robots.
- Study field performance, identify the main failure modes, and improve models through data collection and retraining.
What they’re looking for
- A bachelor's or master's degree in robotics, computer science, electrical engineering, or a related field.
- At least three years of experience applying machine learning to robot manipulation, visuomotor control, or sequence models.
- Strong PyTorch skills and experience building dependable training and evaluation pipelines.
- Solid Python software engineering and the ability to collaborate across ML and robotics teams.
Nice to have
- A PhD in a related field.
- Experience with vision-language-action models, behavior cloning, or transformer and diffusion policies for robot control.
- Sim-to-real training experience with tools such as Isaac Sim or MuJoCo, including domain randomization and synthetic data.
- Deploying ML models to edge hardware with ONNX or TensorRT, quantization, and performance profiling.
- Experience with safety-critical robotics integration and designing fallback and recovery behaviors.
What’s on offer
- Remote working arrangement based in the United States.
Skills
Questions about this role
Is this ML role remote?
Yes, it is a remote role based in the United States.
How much experience is needed?
At least three years of experience applying ML to robot manipulation, visuomotor control, or sequence models.
Do I need a degree?
A bachelor's or master's degree in robotics, computer science, electrical engineering, or a related field is required, and a PhD is a plus.