Research Engineer, World Models

About 1X
We’re an AI and robotics company based in Palo Alto, California, on a mission to build a truly abundant society through general‑purpose robots capable of performing any kind of work autonomously.
We believe that to truly understand the world and grow in intelligence, humanoid robots must live and learn alongside us. That’s why we’re focused on developing friendly home robots designed to integrate seamlessly into everyday life.
We’re looking for curious, driven, and passionate people who want to help shape the future of robotics and AI. If this mission excites you, we’d be thrilled to hear from you and explore how you might contribute to our journey.

Role Overview
You will build large multi‑modal generative “world models” that predict future sensor inputs and actions of the robot from its past observations. These foundational models are meant to enable the robot to understand and act in unstructured, real‑world environments. You will work across data pipelines, model architecture, and product deployment to drive improvements in robot autonomy.

Responsibilities

• Full‑stack engineering: data engineering, model architecture design, and delivering polished products

• Develop high‑throughput data loaders for large multi‑modal datasets

• Implement tokenizers and transformers tailored for web‑scale robot data

• Translate improvements in world model architectures into improvements in robot autonomy

• Predict how real‑world robot performance scales with pre‑training metrics (e.g., log loss)