RL Researcher: Robot Learning for Real-World Deployment

AIT Community; San Carlos (CA); Hybrid; USD 200,000 - 300,000; Full time

Benefits offered by this job

Medical, dental, vision

Paid time off

401(k) with company match

Commuter benefits

Onsite meals

Parental leave

Job summary

1X is building humanoid home robots designed to perform chores and tasks safely and reliably. We are hiring researchers to advance RL from simulation to real-world deployment, enabling robots to operate in people’s homes with dependable performance.

You will own end-to-end RL pipelines for manipulation and locomotion, collaborating with hardware and QA teams to ship production-ready policies to customer sites.

Qualifications

• Strong Python and C++ with experience in large codebases.
• Proficiency with PyTorch for RL policy training.
• Hands-on experience with simulation platforms (Isaac Sim, MuJoCo) for policy training at scale.
• Demonstrated experience training RL policies for manipulation or locomotion and addressing sim-to-real gaps.

Responsibilities

• Train and deploy RL policies for manipulation and locomotion tasks in real-world home environments.
• Advance sim-to-real transfer techniques to narrow the gap between simulation and real-world policy behavior.
• Build training and evaluation infrastructure for rapid iteration with standardized benchmarks and regression detection.
• Partner with hardware, controls, data, and QA teams to ship RL-trained skills to production customer sites.

Skills

Python

C++

PyTorch

RL policy training

Tools

Isaac Sim

MuJoCo

Bazel

Job description

1X is building humanoid home robots designed to perform chores and tasks safely and reliably. We are hiring researchers to advance RL from simulation to real-world deployment, enabling robots to operate in people’s homes with dependable performance.

You will own end-to-end RL pipelines for manipulation and locomotion, collaborating with hardware and QA teams to ship production-ready policies to customer sites.