Founding Machine Learning - World Models

One Robot; San Francisco, Northern (CA, KY); Hybrid; USD 150,000 - 210,000; Full time

Job summary

One Robot in San Francisco builds world models that simulate manipulation scenes to validate, and one day train policies without touching a robot. You will develop generative models with controllability and fidelity to match real-robot behavior.

You will train video and dynamics models, push long-horizon coherence, own training infrastructure across multi-GPU clusters and write custom CUDA, and design a data engine to compound learning across tasks.

Qualifications

• Strong coding in Python and PyTorch (or similar).
• Video generation experience: deep experience training image or video generation models end-to-end.
• Large-scale training: track record operating training runs at cluster scale.
• 3D vision: working knowledge of multi-view geometry, scene reconstruction, and physical priors.

Responsibilities

• Train video and dynamics models: develop world models with action conditioning for manipulation policies.
• Push long-horizon coherence: develop architectures and training methods that extend rollout quality on hard physical tasks.
• Own training infrastructure: run multi-GPU clusters, write custom CUDA, debug at scale.
• Build the world-model data engine: design, implement, and improve a data engine that allows learning across customers and manipulation tasks.

Skills

Python

PyTorch

Video generation

Large-scale training

3D vision

Tools

CUDA

Job description

We build world models that simulate manipulation scenes faithfully enough to validate, and one day, train policies without touching a robot. You'll develop generative models that make this work, with the controllability and physical fidelity to match real-robot behavior.

What you'll do:

• Train video and dynamics models: Develop world models with action conditioning for manipulation policies.

• Push long-horizon coherence: Develop architectures and training methods that extend rollout quality on hard physical tasks.

• Own training infrastructure: Run multi-GPU clusters, write custom CUDA, debug at scale.

• Build the world-model data engine: Design, implement, and improve a data engine that allows the world model to compound learning across customers and manipulation tasks.

Requirements:

• Very strong coding in Python and PyTorch (or similar).

• Video generation experience: Deep experience training image or video generation models end-to-end.

• Large-scale training: Track record operating training runs at cluster scale.

• 3D vision: Working knowledge of multi-view geometry, scene reconstruction, and physical priors.