Work Across
Get started
All jobs
Save

Genesis-World: Core Simulation Engine Engineer

Genesis
Contract type
Ongoing
Work mode
Remote
Experience
3 years

Job description

Core maintainer role for Genesis-World, an open-source general-purpose simulation platform for physical AI, focused on the software engineering backbone: infrastructure, tooling, APIs and architecture. The role aims to remove friction from simulation so roboticists can adopt it more easily.

At a glance

Work mode
Remote

What you'll do

  • Make testing of a JIT-compiled engine scalable, addressing the compile-time to runtime ratio bottleneck jointly with the compiler teams
  • Make any bug reproducible: dump and reload simulations bit-exactly across machines and backends, and turn failing runs into standalone reproduction scripts automatically
  • Make autodiff first-class: drive requirements on Quadrants and iterate with the compiler team until integration is solid
  • Enable editing scenes at frozen time without building the scene or compiling the engine
  • Make the simulator extensible with first-class plugins for physics solvers and interactive viewer backends, including Nyx
  • Give robots real actuation: motors and MIMO transmissions cleanly abstracted at the interface between users and the physics engine
  • Make time a local variable by freeing the clock down to the sub-scene level
  • Make scenes come alive with events triggered by physics
  • Keep the core sharp: refactoring legacy subsystems, stronger typing, consistent coding style, less Python overhead on hot paths, full scene serialization, telemetry and replay
  • Review issues and pull requests with the core team, answer questions from users and contributors, and join the push on adoption
  • Work on infrastructure, tooling, APIs and architecture around the physics algorithms
  • Serve as core maintainer of Genesis-World with shared stewardship of the whole platform from day one

What we're looking for

  • Care about the engineer using what you build as much as the thing itself; go after root causes of slow tests, cryptic errors and manual steps
  • Have opinions about API design
  • Comfortable with physics and robotics
  • Strong Python engineering on large codebases: architecture, refactoring, typing, packaging, performance profiling (py-spy, Nsight, Xcode Instruments, RenderDoc)
  • Developer tooling, test infrastructure, or CI at scale
  • Enough fluency with JIT compilation, code generation, or GPU computing stacks to reason about compilation caching, kernel dispatch, and startup cost
  • At ease debugging across Windows, Linux, and macOS, on x86 and arm64, over CUDA, AMD, and Apple Metal (and possibly Intel XPU via Vulkan soon)
  • Open-source reflexes: triaging issues, reviewing external pull requests, communicating with a community

Nice to have

  • Experience with other robotics simulators (Drake, MuJoCo, Newton, Isaac, RaiSim, Jiminy, Brax)
  • PyTorch, our user-facing interface
  • Other JIT compilers such as Triton, JAX, or Numba
  • 3D tooling and interactive editors (Maya, Blender, Houdini)
  • Serialization formats (USD, glTF, MJCF/URDF)
  • C++, CUDA, or Metal
  • Developer relations or community work

Your team

Genesis-World

The team building an open-source, general-purpose simulation platform for physical AI, with a physics team developing algorithms and a compiler team behind Quadrants.

Apply

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, with a unified multi-physics engine, the Nyx in-house renderer, sensor simulation, and the Quadrants JIT compiler.

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
  • Quadrants is an in-house JIT compiler lowering kernels to CUDA, AMD ROCm, Apple Metal, Vulkan, x86, and ARM64
  • Simulation runs two orders of magnitude faster than hardware, correlating with on-hardware rollouts at 89%
  • Developing the most comprehensive and fastest Incremental Potential Contact solver for deformable body dynamics, soon to be open-sourced