Genesis-World: Core Physics Engineer at Genesis | GB | Rezi

Genesis-World: Core Physics Engineer at Genesis

Genesis-World: Core Physics Engineer

Genesis · GB

2 weeks ago

Genesis-World: Core Physics Engineer

Genesis · GB

16 days ago
Resume preview

Impress employers and recruiters.
Choose from hundreds of resume examples.

Target Resume Now
Resume preview

Tailor your resume to this Genesis-World: Core Physics Engineer role.

Rezi rewrites your resume against Genesis's job description. Free.

Resume score gauge reading 58 out of 100

Don't guess if your resume is good enough.

See how it scores against the Genesis-World: Core Physics Engineer posting at Genesis — free, in seconds.

About the Role

You will push the physics of Genesis-World forward, shipping production-ready simulation capabilities that matter for the company's internal needs. This involves applied research from algorithm to merged, tested, documented code that real robot-learning pipelines depend on, with occasional groundbreaking research through academic collaborations. The core of the job is making the engine measurably better across five axes: Speed, Completeness, Fidelity, Versatility, and Scalability.

Responsibilities

  • Ship production-ready simulation capabilities that matter for the company's internal needs.
  • Conduct applied research from algorithm to merged, tested, documented code.
  • Make the engine measurably better across speed, completeness, fidelity, versatility, and scalability.
  • Invent physics level-of-detail (LOD).
  • Develop solutions for heterogeneous environments.
  • Implement adaptive timesteps per island.
  • Couple everything efficiently and accurately.
  • Develop more scalable constraint solvers.
  • Unify contact resolution.
  • Handle closed kinematic loops without constraints.
  • Write physics in plain Python and ensure Quadrants makes it fast on every backend.
  • Validate physics through analytical closed forms, other engines, and real-world data.

Requirements

  • A physicist and an engineer at once.
  • Ability to judge a method by its production viability at real scale.
  • Relentlessly hunt down insignificant defects.
  • 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).
  • 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.
  • Publications in simulation, graphics, or robotics venues (SIGGRAPH, ICRA, IROS, CoRL, RSS) are a plus.
  • Contributions to an open-source physics engine are a plus.

Skills

  • Physics-based simulation
  • Robotics simulation
  • RBD
  • FEM
  • MPM
  • SPH
  • IPC
  • XPBD
  • VBD
  • ABD
  • Constrained optimization
  • Numerical integration of stiff systems
  • HPC programming (CPU and/or GPU)
  • Python
  • CUDA
  • AMD ROCm
  • Apple Metal
  • Vulkan

Location

  • Remote

Work Type

  • Full-time

Experience Level

  • Mid-level
  • Senior

About the Company

  • Genesis AI is building Genesis-World, an open-source, general-purpose simulation platform for physical AI.
  • Genesis-World features a unified multi-physics engine supporting rigid bodies, FEM, MPM, particles, cloth, and fluids.
  • The platform includes an in-house renderer, Nyx, for real-time photorealistic rendering.
  • It supports a wide range of sensors and advanced tactile simulation.
  • The engine is powered by an in-house JIT compiler, Quadrants, which optimizes code for various backends including CUDA, AMD ROCm, Apple Metal, Vulkan, x86, and ARM64.
  • Genesis-World is designed for massively batched GPU simulation for learning at scale and complex non-batched scenes.
  • The platform is central to Genesis AI's strategy to overcome the evaluation bottleneck in scalable robotics.
  • The goal is to establish Genesis-World as the go-to simulator for physical AI.