RL Engineer — Dexterous Grasping for Real Robots

Persona AI Inc; Houston (TX); On-site; USD 120,000 - 180,000; Full time

Benefits offered by this job

Performance-based bonus

Medical benefits 99% covered

Early-stage equity

Paid time off

Job summary

Persona AI Inc. seeks a Reinforcement Learning Engineer to advance dexterous grasping on real hardware. You will design RL policies, bridge sim-to-real gaps, and craft reward structures for high‑DOF hands.

You will train in MuJoCo/Isaac Lab, iterate on real robots, and push state-of-the-art research into production on a humanoid platform. Strong Python, PyTorch, and JAX skills are essential.

Qualifications

• Requires a degree in Robotics, CS, or ML (BS/MS/PhD).
• 2+ years hands-on RL for robotic manipulation.
• Ability to read, understand, and implement recent robotics/ML research.
• Experience training RL agents for robotic manipulation with reward shaping.
• Experience with sim-to-real transfer: domain randomization, physics tuning, or real-world validation.
• Proficiency in Python and DL frameworks (PyTorch, JAX) and RL libraries (rsl_rl, skrl).
• Experience with meshes/collision geometries for RL environments in MuJoCo/Isaac Sim.

Responsibilities

• Train and iterate RL policies for complex grasping tasks (functional grasping, tool use, in-hand manipulation).
• Develop sim-to-real transfer pipelines to bridge simulation and hardware performance.
• Develop reward functions, curricula, and training environments in MuJoCo and Isaac Lab.
• Run experiments on real robots and in simulation, debug and evaluate policies on hardware.
• Monitor and adapt state-of-the-art research for deployment on humanoid platform.
• Collaborate with software team to deploy end-to-end grasping systems.
• Benchmark policies across object diversity and real-world uncertainties.
• Integrate tactile sensing and feedback into grasp policies for robust manipulation.

Skills

Reinforcement learning

Robotic manipulation

Python

PyTorch

JAX

Deep learning

Education

BS/MS/PhD in Robotics, CS, or ML

Tools

MuJoCo

Isaac Sim

rsl_rl

skrl

Job description

Persona AI Inc. seeks a Reinforcement Learning Engineer to advance dexterous grasping on real hardware. You will design RL policies, bridge sim-to-real gaps, and craft reward structures for high‑DOF hands.

You will train in MuJoCo/Isaac Lab, iterate on real robots, and push state-of-the-art research into production on a humanoid platform. Strong Python, PyTorch, and JAX skills are essential.