Robotics Research Engineer / Scientist — Robot Learning

Description

The company is hiring a Robotics Research Engineer or Scientist to build learning-based methods that let robots carry out complex tasks in the real world.

The work centres on robot learning, policy training and deployment on physical hardware. You will try approaches like imitation learning, reinforcement learning and Vision-Language-Action (VLA) models, and turn research ideas into policies that run on real robotic systems, closing the gap between research and practical capability.

The role suits someone with strong robotics or machine learning background who likes hands-on experimentation and extending what learning-based robots can do.

Responsibilities

• Build and train learning-based policies for robotic manipulation and other embodied tasks.
• Use imitation learning, reinforcement learning, diffusion policies and VLA models.
• Work on visuomotor policies, bimanual and dexterous manipulation, and generalization across tasks or environments.
• Create data collection and training pipelines based on robot demonstrations and other relevant datasets.
• Put trained policies on physical robots and debug their behaviour in real environments.
• Design careful experiments that measure task success, robustness and generalization.
• Study failures and refine data, model architectures and training methods to raise performance.
• Work with infrastructure, simulation and data teams to speed up robot learning research.

Requirements

• A PhD in Robotics, Computer Science, Machine Learning or a related field, or substantial hands-on experience building learning-based robotic systems as an alternative. Strong MS candidates are welcome.
• Strong Python skills and experience with deep learning frameworks such as PyTorch.
• Experience with at least one learning-based robotics approach, such as imitation learning, reinforcement learning, diffusion policies or VLA models.
• Understanding of robotic manipulation, perception, control or visuomotor learning.
• Experience designing and running experiments to evaluate learned policies.
• Strong problem-solving skills and the ability to turn research ideas into working systems.
• Optional: experience deploying learned policies on real robots.
• Optional: experience with bimanual or dexterous manipulation.
• Optional: experience collecting and processing robot demonstration data.
• Optional: experience improving task success rates, robustness or generalization through model or data changes.
• Optional: research publications or contributions to open-source robotics and ML projects.
• Experience with ROS integration or traditional control systems alone does not meet the bar; the company prioritises hands-on work with learning-based robotic systems.

Conditions

The company is an equal opportunity employer.

Benefits

• Health insurance
• Vision care
• Dental coverage
• 401(k)
• Paid holidays
• PTO (Paid Time Off)
• Sick leave