About this role
About The Company
General Intuition is the frontier lab for acting in space and time. We build large action models and world models that can perceive, predict, and act across virtual and physical environments. General Intuition builds on the strength of Medal, the world's largest and fastest-growing platform for gaming clips, where millions of gamers capture, share, and discover new games every year. We've raised over $650M from Khosla, GC, Valor, and Point72 since October 2025, and recently closed our latest round at a $6.2B valuation.
The Role
We see our stack as three levels: a high-level planner (task, instruction, where to go and what to do), a mid level (our game-trained model, which goes from pixels to short-horizon intent like velocities, tool use, object interactions), and a low level (per-robot controllers that turn that into actual motion). The sim training role grows this in two directions: vertically, going deeper in the action space by training the low-level controllers in sim + RL for each robot and defining the interface with the mid level; and wider, building more environments that are realistic enough to train in and not just eval.
This is an in-person role in one of our New York, Geneva, or Zurich offices.
What We're Looking For
- Deep, hands-on simulation experience, run in production. We run on Isaac Sim, Isaac Lab and MuJoCo; what matters is that you've owned environments, assets and domain randomization in a major simulator, and physics at a fidelity where contact models, actuator dynamics and solver settings were your decisions.
- 6+ years of hands-on exposure to robot learning in simulation (contact-rich manipulation, legged locomotion, whole-body control, or similar), with strong fundamentals in reinforcement learning, controller design and sim-to-real transfer.
- Proven ability to bridge simulation and real-world robotic systems. You've deployed simulation-trained policies on real robots, across more than one embodiment, and you've quantified the sim-to-real gap rather than assumed it.
- A track record of building simulation from scratch, not just training in what someone else designed, ideally as the first simulation engineer on a team, and evidence that other people came to depend on what you built.
- Experience leading simulation while staying hands-on: you've set technical direction and raised the bar of the engineers around you, ideally including hiring them, and you still write code today.
- Range across the whole stack, from the solver and the low-level controller up through the policy.
Compensation
$350K – $500K • Offers Equity