Genesis-World: Core Physics Engineer

Genesis

Contract type

Ongoing

Work mode

Remote

Experience

3 years

Job description

A physics simulation engineer role at Genesis AI, pushing the physics of the open-source Genesis-World simulator forward. The role focuses on shipping production-ready simulation capabilities that improve speed, completeness, fidelity, versatility and scalability for robot learning.

At a glance

Work mode: Remote
Languages: English

What you'll do

Push the physics of Genesis-World forward, shipping production-ready simulation capabilities that matter for the company's internal needs
Do research applied end-to-end, from algorithm to merged, tested, documented code that real robot-learning pipelines depend on
Improve the engine along five axes: speed, completeness, fidelity, versatility and scalability
Develop algorithms that spend compute only where it matters across time and space: larger stable timesteps, selective fidelity, structure-aware solvers
Extend the engine to cover any physics needed by the next use-case: water, human animation, air flow, gravel, tendons, even body organs
Build more realistic models: contact, friction, deformation, energy, actuation, materials
Enable extensible multi-physics with all solvers in the scene coupled together at once, two-way and constraint-based
Scale from workstation to factory scale and one day city scale: thousands of interacting entities, batched across environments, without losing physical soundness
Write physics in plain Python, with Quadrants making it fast on every backend
Validate physics the hard way: analytical closed forms, other engines, real-world data
Work on problems such as physics level-of-detail, heterogeneous environments, adaptive timesteps per island, exact two-way constraint-based coupling between grey-box solvers using methods like ADMM, more scalable constraint solvers, unified contact resolution, and closed kinematic loops without constraints

What we're looking for

Physicist and engineer at once, judging a method by whether it holds up in production at real scale
Relentlessly hunts down even the defect that looks insignificant
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

Nice to have

Publications in simulation, graphics, or robotics venues (SIGGRAPH, ICRA, IROS, CoRL, RSS)
Contributions to an open-source physics engine

Save

Direct apply at Genesis

Opens the job posting at Genesis

About Genesis AI

Genesis AI builds Genesis-World, an open-source, general-purpose simulation platform for physical AI. It is one unified multi-physics engine covering rigid bodies, FEM, MPM, particles, cloth and fluids, with the in-house Nyx renderer, sensors of every kind, and an in-house JIT compiler called Quadrants.

Mission

Physical AI that improves at the speed of compute.

Key facts

Genesis-World is an open-source, general-purpose simulation platform for physical AI
One unified multi-physics engine: rigid bodies, FEM, MPM, particles, cloth, fluids
Nyx is the in-house renderer for robotics with real-time photo-realistic rendering
Sensors include cameras, lidar, IMU, contact forces, temperature, and advanced tactile simulation
Developing internally an Incremental Potential Contact solver for deformable body dynamics, soon to be open-sourced
Everything is Python-first and runs anywhere; Quadrants lowers kernels to CUDA, AMD ROCm, Apple Metal, Vulkan, x86, and ARM64
Simulation runs two orders of magnitude faster than hardware (tens of thousands of episodes in half an hour instead of 200+ hours), correlating with on-hardware rollouts at 89%