Robotics Simulation Engineer — Platform & Performance

Socket.dev; San Francisco (CA); On-site; USD 140,000 - 190,000; Full time

Job summary

Weave is seeking a seasoned robotics simulation engineer to own and evolve the simulation platform, domains, and asset pipelines used across the company. You will drive realistic models, fast GPU-accelerated training loops, and robust sim-to-real validation to shorten hardware iteration cycles.

Ideal candidates have 3+ years in robotics simulation, strong Python and C++, and hands-on experience with Isaac Lab/Isaac Sim, MuJoCo, or Drake.

Qualifications

• 3+ years building simulation or robotics software.
• Hands-on with a modern robotics simulator (Isaac Lab/Isaac Sim, MuJoCo, Drake, or similar).
• Strong Python and C++ and the engineering habits to make a research-facing platform reliable.
• Performance-minded with GPU-parallel workloads and deterministic seeding.

Responsibilities

• Own the sim stack: environments, assets, robot models, and tooling around them, kept current with every hardware revision.
• Model actuator and contact parameters identified against dyno and robot data with the motor control and controls teams.
• Make training fast with GPU-parallel environment throughput, profiling, and the determinism and seeding discipline for reproducibility.
• Serve sim-to-real with system-identification pipelines, domain randomization tooling, and honest side-by-side measurement of sim vs hardware.
• Catch regressions before hardware does with scenario and regression suites running controllers and policies in sim on every change.
• Keep assets true by routing CAD and robot description to sim-ready assets.

Skills

Robotics simulation

Python & C++

GPU performance

Sim-to-real testing

Hardware awareness

Tools

Isaac Lab/Isaac Sim

MuJoCo

Drake

Job description

Weave is seeking a seasoned robotics simulation engineer to own and evolve the simulation platform, domains, and asset pipelines used across the company. You will drive realistic models, fast GPU-accelerated training loops, and robust sim-to-real validation to shorten hardware iteration cycles.

Ideal candidates have 3+ years in robotics simulation, strong Python and C++, and hands-on experience with Isaac Lab/Isaac Sim, MuJoCo, or Drake.