Reinforcement Learning Engineer (Robotics)

Location: San Carlos, CA, United States. On-site.

Salary: $130,146–$300,000 per year.

Company

hirify.global develops in-home humanoid robots.

What you will do

• Develop sim2real reinforcement learning training pipelines for humanoid robots.
• Train and test robot policies for in-home humanoid robots.
• Optimize training pipelines for performance and speed.
• Model robot dynamics, sensors, contacts, and other physical systems to reduce simulation-to-hardware gaps.
• Collect, clean, and retarget human motion data for reinforcement learning.
• Test and debug reinforcement learning policies in simulation and on physical hardware.

Requirements

• Master’s degree or foreign degree equivalent in Robotics, AI/Machine Learning, Mechanical or Electrical Engineering, Computer Science, or a related field.
• At least one year of experience in a Robotics & Machine Learning occupation or a related role.
• Experience with rigid-body dynamics and/or dynamical systems for training, deploying, and testing reinforcement-learned policies for humanoid robots.
• Ability to implement production-grade Python code for reinforcement learning and other machine learning training pipelines.
• Knowledge of reinforcement learning algorithms, techniques, and sim2real approaches for robotics and human-like capabilities, including whole-body loco-manipulation.
• Ability to implement and debug real-time C++ software deployed on robots under real-time constraints.
• Experience modeling multi-body hybrid dynamic systems with contact in simulation and identifying gaps between simulation and hardware.
• Root-cause analysis and rapid troubleshooting of robotic systems.
• Forward and inverse kinematics for humanoid system training using human motion data.

Culture & Benefits

• Full-time, on-site work in San Carlos, California.
• Work in the Artificial Intelligence department on physical humanoid robots and reinforcement learning systems.