Research Engineer Scientist Simulation Dyna-Robotics

Overview

As a Research Engineer Scientist focused on Simulation you will build the simulated worlds that power Dyna`s loco-manipulation policies. Our robot is a wheeled mobile manipulator. Mobility and manipulation are tightly coupled so simulating one without the other misses what actually matters for our policies. You`ll own the pipeline end-to-end from real-to-sim reconstruction of the facility-scale environments our robots navigate through procedural scene generation to sim-based training data and evaluation for policies that jointly control base motion and arm manipulation. This is a founding-type ownership role that defines its own research agenda.

What You'll Do11

• 1Build a pipeline that reconstructs real facility-scale environments into simulation including full rooms and aisles not just tabletop scenes
• 2Procedurally generate navigable environments that stress-test loco-manipulation policies across the range of spaces our robots actually operate in
• 3Generate synthetic training data for policies that jointly reason about base positioning and arm manipulation such as approach angles reachability and obstacle-aware repositioning and feed real-world failure modes back into new sim scenarios
• 4Build simulation benchmarks that test the joint base+arm policy using VLA imitation learning or diffusion models as a whole not manipulation in isolation on a fixed base
• 5Render photorealistic visuals specifically to close the sim-to-real gap for vision-based loco-manipulation ensuring rendering fidelity is a first-class deliverable
• 6Partner with the AI Research team on where simulated data and evaluation most accelerate loco-manipulation policy development and with Data Ops on what`s worth capturing in the real world versus generating in sim
• 7Bring MS or PhD in CS Robotics Graphics or equivalent hands-on experience demonstrating depth in building simulation rendering systems
• 8Show hands-on experience with simulation stacks like MuJoCo Isaac Sim/Isaac Lab SAPIEN Omniverse or Blender for robotics or graphics
• 9Experience with procedural scene asset generation domain randomization or photorealistic rendering pipelines at scale not academic-scale one-off scenes
• 10Familiarity with training/evaluating manipulation or loco-manipulation policies such as imitation learning VLA diffusion or RL and how simulated data feeds into them
• 11Experience simulating mobile bases wheeled tracked or holonomic is a real plus

Salary Insight