← All roles

Research Scientist, Simulation

DYNA Robotics· Research
Apply on company site
Redwood City, CAFull-timePosted 2mo ago

About the role

Research Scientist focused on Simulation to build simulated worlds for loco-manipulation policies of a wheeled mobile manipulator. End-to-end responsibilities from real-to-sim reconstruction of facility-scale environments to procedurally generated scenes, sim-based data generation, evaluation, and cross-team collaboration to accelerate loco-manipulation policy development.

Responsibilities

  • Real-to-Sim Reconstruction: Build a pipeline that reconstructs real, facility-scale environments into simulation (3D reconstruction, photorealistic re-rendering).
  • Facility-Scale Scene Generation: Procedurally generate navigable environments (layouts, obstacles, object placement) that stress-test loco-manipulation policies across the range of spaces our robots actually operate in.
  • Loco-Manipulation Sim-for-Data-Gen: Generate synthetic training data for policies that jointly reason about base positioning and arm manipulation (approach angles, reachability, obstacle-aware repositioning), and feed real-world failure modes back into new sim scenarios.
  • Loco-Manipulation Evaluation: Build simulation benchmarks that test the joint base+arm policy (VLA / imitation learning / diffusion models) as a whole, not manipulation in isolation on a fixed base.
  • Rendering for ML, Not Just Physics: Push photorealistic rendering quality specifically to close the sim-to-real gap for vision-based loco-manipulation.
  • Cross-Team Collaboration: Partner with AI Research and Data Ops to optimize simulated data/evaluation and real-world data capture.

Qualifications

  • MS or PhD in CS/Robotics/Graphics, or equivalent hands-on experience.
  • Hands-on experience with simulation stacks (MuJoCo, Isaac Sim/Isaac Lab, SAPIEN, Omniverse, Blender, or similar).
  • Experience with procedural scene/asset generation, domain randomization, or photorealistic rendering pipelines at scale.
  • Familiarity with training/evaluating manipulation or loco-manipulation policies (imitation learning, VLA, diffusion, or RL).
  • Experience simulating mobile bases (wheeled, tracked, or holonomic) is a real plus.
  • Prior research or engineering background in loco-manipulation or whole-body control.
  • Strong Python skills; comfort with PyTorch or JAX for model training/eval.
  • Senior enough to define your own research agenda and exercise independent judgment.

Skills

Required:3D reconstructionProcedural scene/asset generationPhotorealistic renderingSimulation stacksManipulation policy training/evaluationPythonPyTorch or JAX

Benefits

  • Don’t see explicit benefits listed in text; included benefits are not present in input and therefore omitted.
Last updated Oct 7, 2026. Interested? Apply on the company site.

About DYNA Robotics

Commercial-Grade Robots for Real-World Automation

DYNA: The first production-ready foundation model robot — built to reliably deploy in the wild.

DYNA-1automationcommercial robotsdual-arm robotsfactory automationphysical-ai-funding-landscapereal-world roboticsrestaurant automation
Company profileWebsite

More open roles at DYNA Robotics