Robotics Research Engineer: Real-World Policy & Control

Maxinsights; Santa Clara (CA); On-site; USD 130,000 - 180,000; Full time

Benefits offered by this job

Health insurance

Vision care

Dental coverage

401(k)

Paid holidays

PTO (Paid Time Off)

Sick leave

Job summary

Maxinsights in Santa Clara, CA is seeking a Robotics Research Engineer/Scientist to develop learning-based methods enabling robots to perform complex tasks in the real world, with emphasis on imitation learning, reinforcement learning, and Vision-Language-Action models.

You will train and deploy visuomotor policies on physical robots, design data collection pipelines from demonstrations, and run rigorous experiments to measure task success, robustness, and generalization.

Qualifications

• PhD (or substantial hands-on) in robotics, CS, ML, or related field.
• Strong programming in Python and DL frameworks (PyTorch).
• Experience with learning-based robotics approaches (RL/IL/VLA).
• Understanding of robotic manipulation, perception, control, or visuomotor learning.

Responsibilities

• Develop and train learning-based policies for robotic manipulation and embodied tasks.
• Apply imitation learning, reinforcement learning, diffusion policies, and VLA models.
• Design data collection and training pipelines using robot demonstrations.
• Deploy trained policies on physical robots and debug real-world performance.
• Design rigorous experiments to evaluate success, robustness, and generalization.
• Collaborate with infra, simulation, and data teams to accelerate research.

Skills

PhD or equivalent

Python

PyTorch

Reinforcement learning

Imitation learning

Robotics perception

Education

PhD in Robotics/CS/ML or related

Tools

ROS

Git

Gazebo

Job description

Maxinsights in Santa Clara, CA is seeking a Robotics Research Engineer/Scientist to develop learning-based methods enabling robots to perform complex tasks in the real world, with emphasis on imitation learning, reinforcement learning, and Vision-Language-Action models.

You will train and deploy visuomotor policies on physical robots, design data collection pipelines from demonstrations, and run rigorous experiments to measure task success, robustness, and generalization.