Leads the team this role joins
Hires for this team
On the team, can refer you
From your own Gmail and LinkedIn.
About the role
This is a full-time, on-site role in Santa Clara, California, for a simulation engineer who builds the pipeline from real-world capture into simulation. It suits engineers strong in Python and C++ who can calibrate robot and object models so that simulated behavior matches physical hardware. The work centers on reconstructing robots, objects and scenes, then delivering SimReady assets for training, evaluation and policy transfer. The role spans computer graphics, rigid-body dynamics and data collected from physical robots.
What you’ll do
- Own the Real2Sim workflow in Isaac Sim, MuJoCo, Genesis, Blender and similar tools, from 3D reconstruction through contact and inertia calibration.
- Create, validate and iterate SimReady assets in USD, URDF and MJCF, including joints, collision shapes, mass properties and semantic labels.
- Process captured camera, point cloud and mesh data, and calibrate textures and PBR materials.
- Use 3D Gaussian Splatting and NeRF methods to digitize real scenes into simulation-ready assets.
- Build tools for calibration, data processing and asset quality checks, and document the workflows and metrics.
- Design excitation trajectories for system identification, collect dynamic data from physical robots, and reproduce nonlinear joint behavior.
- Work with perception, learning, simulation and hardware teams on sim-to-real benchmarks.
What they’re looking for
- Skill in Python and C++ for writing calibration scripts, engine plugins and data processing utilities.
- Proficiency in at least one simulation or graphics tool such as Isaac Sim, MuJoCo, Genesis or Blender, with a sound grasp of computer graphics and rigid-body dynamics.
- Familiarity with physics engines such as PhysX and Newton.
- Hands-on experience with Real2Sim pipelines and SimReady asset standards.
- Knowledge of 3D reconstruction, camera imaging, point cloud processing and camera calibration.
- A working understanding of system identification, parameter calibration and contact or friction models, plus familiarity with PBR rendering.
- Ability to root-cause sim-to-real mismatches and run comparative experiments.
- Strong data analysis, experimental design and engineering delivery skills.
Nice to have
- A track record of Real2Sim projects, especially for robotic arms, dexterous hands or humanoid robots.
- Deep familiarity with USD, URDF and MJCF, plus experience building asset libraries and automated validation.
- Experience with 3DGS, NeRF, PBR reconstruction and photogrammetry.
- Background in excitation trajectory design, dynamic parameter estimation and contact model tuning.
- Knowledge of nonlinear friction models such as LuGre and Stribeck, and of joint hysteresis and backlash.
- Experience with motion capture, multi-sensor calibration and real robot hardware experiments.
- Exposure to VLA models, world models, diffusion policy, reinforcement learning or domain randomization.
What’s on offer
- Default benefits include health insurance, vision and dental coverage, a 401(k), paid holidays, PTO and sick leave.
Skills
Questions about this role
Where is this job based?
Santa Clara, California, on site.
What programming languages are required?
Python and C++ are both listed as must-have skills.
What benefits are offered?
Health insurance, vision, dental, a 401(k), paid holidays, PTO and sick leave are listed as default benefits.
What simulation tools should I know?
At least one of Isaac Sim, MuJoCo, Genesis or Blender, with PhysX and Newton familiarity helpful.