Robotics ML & RL Engineer for Real-World Robots

Eka Robotics; Massachusetts; On-site; USD 140,000 - 210,000; Full time

Job summary

Eka Robotics is on a mission to build intelligence for the physical world — robots that are fast, general, and reliable. We combine physics-based insights with learning to push robotics research from theory to real-world deployment.

We seek hands-on researchers who can design RL and supervised learning solutions, build simulation pipelines with domain randomization, evaluate architectures for sample efficiency and real-time performance, and validate policies on real hardware, collaborating

Qualifications

• Advanced degree in CS/Robotics or related field.

Responsibilities

• Research and implement reinforcement learning and supervised learning algorithms for robotic manipulation.
• Design simulation models and domain randomization strategies; collaborate with the robotics team to ensure alignment with physical systems.
• Performance optimization: design experiments to evaluate and optimize model architectures for sample complexity and policy performance with real-time execution constraints.
• Data & Pipeline Engineering: develop scalable data management pipelines for real and synthetic data; evaluate and select algorithms that maximize data efficiency and overall policy performance.
• On-Robot Evaluation: Deploy, evaluate, and debug policies on physical hardware; identify bottlenecks and implement improvements in collaboration with the robotics team.

Skills

Reinforcement learning

Supervised learning

Python

PyTorch

JAX

Transformers

CNNs

Foundation Models

Robotics

Experimentation

Education

BS/MS/PhD in Computer Science, Robotics, or related field

Tools

Isaac Sim

MuJoCo

PyBullet

ROS/ROS2

Git

Job description

Eka Robotics is on a mission to build intelligence for the physical world — robots that are fast, general, and reliable. We combine physics-based insights with learning to push robotics research from theory to real-world deployment.

We seek hands-on researchers who can design RL and supervised learning solutions, build simulation pipelines with domain randomization, evaluate architectures for sample efficiency and real-time performance, and validate policies on real hardware, collaborating