Simulation Researcher/Engineer

Luma
Redwood City
Workplace: HybridFull timeFunction: Research & Scientific (R&D)Skills: ["Collaboration","System design","Problem-solving","Ownership","Communication"]

Design hybrid simulation environments that combine generative rollouts with physics-engine scenes for training general-purpose robot policies. Build evaluation harnesses to measure sim-to-real gap, physical consistency, and long-horizon coherence, then develop differentiable, GPU-accelerated simulation pipelines. Lead asset, scene, and task generation (using Luma’s generative stack) and partner closely with world-model and policy-learning researchers.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Luma
Luma
2 weeks ago

Simulation Researcher/Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 6 hours agoStatus: Live

Job Summary

Design hybrid simulation environments that combine generative rollouts with physics-engine scenes for training general-purpose robot policies. Build evaluation harnesses to measure sim-to-real gap, physical consistency, and long-horizon coherence, then develop differentiable, GPU-accelerated simulation pipelines. Lead asset, scene, and task generation (using Luma’s generative stack) and partner closely with world-model and policy-learning researchers.
Location: Redwood City
Workplace: Hybrid
Employment Type: Full time
Job Function: Research & Scientific (R&D)

Key Responsibilities

  • •Design visually rich, physically plausible, trainable simulation environments that blend generative rollouts and physics-engine scenes.
  • •Build evaluation harnesses to determine whether the world model is sufficient for robot training (sim-to-real gap, physical consistency, long-horizon coherence).
  • •Develop differentiable and GPU-accelerated simulation pipelines that unlock new training signal.
  • •Drive asset, scene, and task generation pipelines, including bootstrapping diversity with Luma’s generative stack.
  • •Collaborate with world-model researchers and policy-learning researchers to integrate simulations into end-to-end training.

Key Requirements

  • •Strong background in robotics simulation, computer graphics, physics-based modeling, or generative 3D, by degree or practical record.
  • •Fluency in Python and C++, and deep familiarity with at least one production physics engine (Isaac Sim/Lab, MuJoCo, Bullet, PhysX, Drake).
  • •Track record building simulation systems that others actually used.
  • •Experience building evaluation harnesses for sim-to-real gap and physical consistency/long-horizon coherence.
  • •Ability to develop differentiable and GPU-accelerated simulation pipelines that improve training signal.
Experience:Robotics simulationComputer graphicsGenerative 3DSim-to-realDifferentiable simulation
Skills:CollaborationSystem designProblem-solvingOwnershipCommunication
Tech Stack:PythonC++Isaac Sim/LabMuJoCoBulletPhysXDrakeGPU-accelerated simulationDifferentiable simulationNeural rendering

Company Brief

Luma
Develops AI-powered tools for capturing, editing, and rendering high-quality 3D scenes from photos and videos, enabling creators to generate photorealistic 3D assets and spatial experiences.
Industry: AR/VR & Spatial Computing
Website