Dexterous Robotics Research Scientist Intern

Meta; Redmond (WA); On-site; USD 20,000 - 33,000; Full time

Job summary

Agios, a full stack research organization within Reality Labs Research, seeks a Research Scientist Intern to advance fast, stable, learned feedback control for multi‑fingered robotic hands. You will focus on reinforcement learning in high‑fidelity simulation, tactile feedback, and transfer to real robot hands.

Internships span 12–24 weeks with multiple start dates yearly, offering exposure to hardware, simulation, controls, and policy learning in a collaborative team setting.

Qualifications

• PhD in Computer Science, Robotics, Mechanical or Electrical Engineering or a related field.
• Research experience in reinforcement learning or learning-based control for robotic manipulation or locomotion.
• Experience with Python and physics simulators MuJoCo, Isaac, or Drake.
• Must obtain work authorization for employment country and maintain it during employment.
• Proven track record of significant results (grants, fellowships, patents, and first-authored publications).
• Experience with sim-to-real transfer of contact-rich manipulation policies, including domain randomization.
• Experience with tactile sensing, force/torque sensing, or contact estimation in policy learning or control.
• Experience in retargeting for locomotion or manipulation.
• Grounding in manipulation mechanics and control, such as contact modeling, impedance/admittance control, and trajectory optimization.
• Hands-on experience with multi-fingered robotic hands or grippers on real hardware.
• Ability to work cross-functionally in a team environment.
• Availability for minimum 16 consecutive weeks internship.

Responsibilities

• Drive an independent research thread on learned reactive control for dexterous hands from problem formulation through simulation and real-robot evaluation.
• Design controlled experiments and benchmarks isolating issues with manipulation dexterity.
• Integrate proprioceptive signals into control policies and close the sim-to-real gap.
• Collaborate with hardware, simulation, controls, and policy researchers and communicate results.

Skills

Reinforcement learning

Python programming

Sim-to-real transfer

Robotics control

Education

PhD in Computer Science / Robotics / Mechanical / Electrical Engineering

Tools

MuJoCo

Isaac

Drake

Job description

Agios, a full stack research organization within Reality Labs Research, seeks a Research Scientist Intern to advance fast, stable, learned feedback control for multi‑fingered robotic hands. You will focus on reinforcement learning in high‑fidelity simulation, tactile feedback, and transfer to real robot hands.

Internships span 12–24 weeks with multiple start dates yearly, offering exposure to hardware, simulation, controls, and policy learning in a collaborative team setting.