Research Engineer/Scientist, Simulation
On-siteRedwood City, California, United States
Job Summary
Build real-to-sim reconstruction pipelines for facility-scale environments and develop procedural scene generation to stress-test loco-manipulation policies. Own the end-to-end simulation pipeline, including sim-based training data creation, evaluation benchmarks for joint base and arm control, and photorealistic rendering to close the sim-to-real gap. Collaborate with AI Research and Data Ops teams to align simulated data generation with policy development needs. This role defines the research agenda for Dyna's proprietary embodied AI foundation model, leveraging proprietary simulation stacks to train policies that generalize across varied commercial environments.
Required 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) for robotics or graphics
- Experience with procedural scene/asset generation, domain randomization, or photorealistic rendering pipelines at scale (not academic-scale one-off scenes)
- Familiarity with training/evaluating manipulation or loco-manipulation policies (imitation learning, VLA, diffusion, or RL) and how simulated data actually feeds into them
- Strong Python skills; comfort with PyTorch or JAX for anything touching model training/eval
- Senior enough to define your own research agenda and exercise independent judgment on where simulation adds the most leverage
Desired Qualifications
- Experience simulating mobile bases (wheeled, tracked, or holonomic)
- Prior research or engineering background in loco-manipulation or whole-body control itself, coordinating mobile-base motion with arm manipulation, independent of any simulation-specific experience
- Experience with real-to-sim-to-real pipelines (3D reconstruction, NeRF/Gaussian splatting, differentiable rendering)
- Exposure to world-model / video-prediction research (e.g. learned dynamics or latent world models) as a complement to classical physics simulation
- GPU-scale physics simulation experience (CUDA, large-batch parallel sim) rather than single-instance sim
- Background simulating wheeled/mobile manipulators specifically (e.g. Boston Dynamics Stretch, warehouse/logistics robotics) rather than legged humanoids or fixed-base arms
- Publications at CoRL, RSS, ICRA, NeurIPS, CVPR, or SIGGRAPH
- Experience leading or mentoring within a small research team
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.