Research Scientist Intern: Robotic Manipulation & RL

Meta; Redmond; On-site; AUD 78,000 - 118,000; Full time

Job summary

Agios, a research arm within Reality Labs, invites applications for a Research Scientist Intern. You will advance learned feedback control for multi-fingered robotic hands, focusing on reinforcement learning in realistic simulation and sim-to-real transfer to real hardware.

Internships run 12–24 weeks with multiple start dates. Candidates should have a PhD in a relevant field and evidence of impactful research, including publications or open-source work, and familiarity with Python and physics

Qualifications

• PhD in Computer Science, Robotics, Mechanical or Electrical Engineering, or relevant field.
• Research in reinforcement learning or learning-based control for manipulation or locomotion.
• Experience with Python and physics simulators such as MuJoCo, Isaac, or Drake.

Responsibilities

• Work on fast, stable learned feedback control for multi-fingered robotic hands.
• Advance reinforcement learning in high-fidelity simulation and transfer to real robots.
• Collaborate with hardware, simulation, controls, and policy teams on projects.
• Contribute to publications, open-source code, or significant project results.

Skills

Reinforcement learning

Learning-based control

Python

Sim-to-real transfer

Multi-fingered hands

Cross-functional communication

Education

PhD in Computer Science, Robotics, Mechanical or Electrical Engineering

Tools

MuJoCo

Isaac

Drake

Job description

Agios, a research arm within Reality Labs, invites applications for a Research Scientist Intern. You will advance learned feedback control for multi-fingered robotic hands, focusing on reinforcement learning in realistic simulation and sim-to-real transfer to real hardware.

Internships run 12–24 weeks with multiple start dates. Candidates should have a PhD in a relevant field and evidence of impactful research, including publications or open-source work, and familiarity with Python and physics