Robots will learn in simulation before they hit the factory. Genesis-World is our bet on that future.
Genesis-World is an open-source, general-purpose simulation platform for physical AI from Genesis AI. One unified multi-physics engine: rigid bodies, FEM, MPM, particles, cloth, fluids. A robot arm can pour water onto sand, grasp a deformable object, or cut a soft body, all in the same simulation. Nyx, our in-house renderer, may be the most promising renderer for robotics out there: real-time photo-realistic rendering, advanced features like depth of field, and state-of-the-art techniques never seen before. Sensors of every kind: cameras, lidar, IMU, contact forces, temperature, plus arguably the most advanced tactile simulation available (paper). And the engine keeps growing: we are developing internally the most comprehensive and fastest Incremental Potential Contact (paper) solver for deformable body dynamics we know of, soon to be open-sourced. It powers real business applications, from full-fledged box packaging with labelling machine and all, to wire harnessing and lab automation, without any physics hack or compromise.
Everything is Python-first and runs anywhere. Kernels are written once, and Quadrants, our in-house JIT compiler, lowers them to CUDA, AMD ROCm, Apple Metal, Vulkan, x86, and ARM64. A single laptop or a datacenter. Massively batched GPU simulation for learning at scale, and complex non-batched scenes where CPU wins outright.
This is at the core of Genesis AI's strategy. Evaluation is the bottleneck of scalable robotics: real hardware caps iteration at wall-clock time, but simulation turns it into a compute problem. Ours already runs two orders of magnitude faster than hardware (tens of thousands of episodes in half an hour instead of 200+ hours), while correlating with on-hardware rollouts at 89%. The north star: physical AI that improves at the speed of compute.
The roleYou push the physics of Genesis-World forward. The mandate is clear: ship production-ready simulation capabilities that matter for the company's internal needs. Research applied end-to-end, from algorithm to merged, tested, documented code that real robot-learning pipelines depend on. Occasional groundbreaking research happens, notably through academic collaborations. But the core of the job is making the engine measurably better along five axes:
Speed. Algorithms that are not only faster but also smart enough to spend compute only where it matters across both time and space: larger stable timesteps, selective fidelity (adaptive across scales or simply hand-set), structure-aware solvers.
Completeness. No physics off limits: water, human animation, air flow, gravel, tendons, even body organs. Whatever the next use-case needs, the engine grows to cover it.
Fidelity. More realistic models: contact, friction, deformation, energy, actuation, materials…
Versatility. Extensible multi-physics without compromise on realism: all solvers in the scene coupled together at once, two-way and constraint-based. Write your own solver and it joins the scene like a native one, growing into an open solver ecosystem.
Scalability. From workstation to factory scale, and one day, city scale: thousands of interacting entities, batched across environments, without losing physical soundness.
Our ambition is to establish Genesis-World as the go-to simulator for physical AI, from companies and research labs to individuals.
The problems waiting for youEvery fidelity for every physics. The same physics at every point of the speed-accuracy spectrum, from heavily batched training with XPBD or VBD to final validation with IPC. Same scene, same API, pick your tradeoff.
Invent physics level-of-detail (LOD). Rendering has had LOD for decades, physics is still waiting. Simulate at full fidelity what agents interact with and see, coarsely what they do not.
Heterogeneous environments. Every parallel world can hold a completely different model: different bodies, joints, and collision geometries.
Adaptive timesteps per island. Error-based control with Runge-Kutta Dopri5, and Time-of-Impact stepping during collision detection, as done in Jiminy.
Couple everything, exactly. Efficient and accurate two-way constraint-based coupling between heterogeneous grey-box solvers, using state-of-the-art methods like ADMM. Owning every solver in the stack is what makes it possible.
More scalable constraint solvers. Push rigid constraint solving beyond its current scalability ceiling (reference).
Unify contact resolution. Hydro-elastic compliance, unilateral constraints, and sequential impulses in the same framework, ideally under one generic formulation.
Closed kinematic loops without constraints. Handle loops intrinsically for numerical stability and speed, in the spirit of Kamino.
Day to day: you write your physics in plain Python and Quadrants makes it fast on every backend. And you validate it the hard way: analytical closed forms, other engines, real-world data.
Who you areYou are a physicist and an engineer at once. You judge a method by whether it holds up in production at real scale, and you do not stop until it does. No blind spots: you relentlessly hunt down even the defect that looks insignificant, because it never is.
A strong background in physics-based simulation, preferably related to robotics: RBD, FEM, MPM, SPH, IPC, XPBD, VBD, ABD, plus constrained optimization and numerical integration of stiff systems.
A track record of shipping simulation code that others rely on, in an engine, in industry, or in a research codebase used beyond its authors.
Solid HPC programming (CPU and/or GPU), and an instinct for what makes a numerical method fast in practice, beyond complexity classes.
Rigor in validation: analytical closed forms, cross-engine consistency, real-world data.
Bonus points: publications in simulation, graphics, or robotics venues (SIGGRAPH, ICRA, IROS, CoRL, RSS). Contributions to an open-source physics engine.
.png){kind=logo}
