Simulation Researcher/Engineer
Remote • Redwood City, CA • FullTime
Posted 2mo ago
Job Location
Redwood City, CA
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
Applied AI Engineer
About the job
Luma is seeking a Simulation Researcher/Engineer to define and build the simulation substrate for training general-purpose robot policies. This role sits at the intersection of generative models and classical physics simulation, focusing on creating a faithful, controllable, and scalable simulation of the world. You will be responsible for designing visually rich and physically plausible simulation environments, building evaluation harnesses to assess world model quality, and developing differentiable, GPU-accelerated simulation pipelines. The position also involves driving asset, scene, and task generation pipelines, leveraging Luma's generative stack, and collaborating with researchers in world modeling and policy learning.
Responsibilities
- Design simulation environments that are visually rich, physically plausible, and trainable at scale, integrating generative rollouts and physics-engine scenes.
- Build evaluation harnesses to assess the quality of the world model for robot training, considering sim-to-real gap, physical consistency, and long-horizon coherence.
- Develop differentiable and GPU-accelerated simulation pipelines to enhance training signals.
- Drive asset, scene, and task generation pipelines, utilizing Luma's generative stack for diversity.
- Collaborate with world-model researchers and policy-learning researchers.
Requirements
- Strong background in robotics simulation, computer graphics, physics-based modeling, or generative 3D, demonstrated through degree or practical experience.
- Fluency in Python and C++.
- Deep familiarity with at least one production physics engine (e.g., Isaac Sim/Lab, MuJoCo, Bullet, PhysX, Drake).
- Proven track record of building simulation systems used by others.