Simulation and Digital Twin Lead

GRAM•San Francisco, CA

About The Position

GRAM is hiring a Simulation and Digital Twin Lead to own the simulation stack and tooling used across the engineering team and build a high-fidelity digital twin of its robot, validated against real hardware. The Controls, Autonomy, and Systems Integration teams will use the simulation to develop and test before running software on the robot. This is a hands-on individual contributor role initially, with an opportunity to build and lead a team as the company grows. The role includes choosing the physics engine and simulation tools, building models from actuators and joints through full-body contact, and validating simulation against hardware data. The lead will also develop site environment simulations from survey data, simulate sensors for perception and motion planning, and scale simulation to run many robots in parallel for policy training and regression testing.

Requirements

  • Deep hands-on experience with physics simulation of articulated robots using a robot simulator such as Isaac Sim or Gazebo, or a physics engine such as MuJoCo or PhysX, including understanding how the contact model works.
  • Experience closing the sim-to-real loop on real hardware by matching simulation to a physical machine through system identification and validation against logged data.
  • Experience modeling actuators, transmissions, and joints in simulation.
  • Strong Python skills and working knowledge of C++.
  • 5+ years of experience; depth in physics simulation and sim-to-real work on real hardware is emphasized over years of experience.

Nice To Haves

  • Experience with legged robots or robots operating on outdoor terrain.
  • Experience with 3D reconstruction of real sites using photogrammetry or similar survey data.
  • Experience with large-scale parallel simulation for policy training, such as Isaac Lab or MJX.
  • Autonomous vehicle simulation experience, with demonstrated work on actuators and joints.

Responsibilities

  • Own the simulation stack and tooling used by the engineering team, including selection of the physics engine.
  • Build a digital twin of the robot, modeling actuators, joints, and full-body contact, and validate it against hardware data.
  • Own sim-to-real work, including system identification and comparison of field logs against simulation.
  • Build simulations of robot work sites, such as towers and substations, using survey data.
  • Simulate cameras, depth sensors, and IMUs to support perception and motion planning.
  • Scale simulation to run many robots in parallel for policy training and regression testing.

Benefits

  • Early equity included in the package.
  • Opportunity to own a domain and build a team as the company grows.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service