Robotics ML & RL Engineer: Real-World Manipulation

Roboticsconnected; Boston (MA); Presencial; USD 140.000 - 210.000; Tempo integral

Resumo da vaga

Eka Robotics is hiring for a hands-on researcher to advance reinforcement learning and supervised learning for robotic manipulation. You will work on simulation, real-world deployment, and data pipelines, collaborating across teams to push performance under real-time constraints.

Applicants should have strong Python expertise, experience with PyTorch or JAX, and a track record of impactful work in robotics or ML, including publications or a solid project portfolio.

Qualificações

• Education: BS, MS, or PhD in Computer Science, Robotics, or a related field.
• Core Expertise: Deep theoretical and practical knowledge of reinforcement learning and supervised learning algorithms.
• Robotics Toolkit: Experience with physics engines (Isaac Sim, MuJoCo, PyBullet) and robotics middleware (ROS/ROS2).
• Architectural Depth: Understanding of Transformers, CNNs, Foundation Models.
• Technical Proficiency: Expert-level Python; proficient in PyTorch or JAX.
• Engineering Rigor: Clean code, version control, reproducible experiments.
• Track Record: Publications in top robotics or ML conferences or strong project portfolio.

Responsabilidades

• Algorithm Development: Research and implement reinforcement learning and supervised learning algorithms for robotic manipulation.
• Simulation: 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.

Conhecimentos

Reinforcement learning

Supervised learning

Transformers

CNNs

Foundation Models

Python

PyTorch

JAX

Clean code

Publications

Formação

BS/MS/PhD in CS/Robotics

Ferramentas

Isaac Sim

MuJoCo

PyBullet

ROS/ROS2

Descrição da vaga

Eka Robotics is hiring for a hands-on researcher to advance reinforcement learning and supervised learning for robotic manipulation. You will work on simulation, real-world deployment, and data pipelines, collaborating across teams to push performance under real-time constraints.

Applicants should have strong Python expertise, experience with PyTorch or JAX, and a track record of impactful work in robotics or ML, including publications or a solid project portfolio.