Principal AI Research Engineer - RL

The role

This person will work as an on-policy RL engineer to create robust robot policies. The role involves developing policies that achieve high success rates for humanoid robots in industrial environments.

What you will do

• Create robust robot policies
• Work on on-policy RL for hardware that learns in the real-world

Required qualifications

• Re-implemented core RL algorithms (SAC, DDPG) from scratch
• Can debug unstable gradients and tune hyperparameters correctly
• Made meaningful intellectual contributions to sample-efficient RL algorithms (e.g., DreamerV3 and MuZero)
• Shipped on-policy RL on hardware that learns in the real-world (e.g., for quadruped walking or drone racing)

Nice to have

• Portfolio or insane project

Benefits

• High equity

About the company

Reflex Robotics builds general-purpose, AI-powered humanoid robots for the toughest jobs in industry. It is a four year old startup backed by Khosla Ventures.