Software Engineer
Simulation Engineer at Menlo builds faithful digital twins for humanoid robots, bridging sim-to-real gaps using physics engines, ROS, C++ and Python to support autonomous locomotion and policy training.
About Menlo
Menlo Research is an Applied R&D lab building Asimov, an open-source humanoid robot platform, and the full software stack that powers it. Our mission is to make humanoid labor economically viable -- turning software into physical labor at scale. We build across the full stack: hardware architecture, locomotion, autonomy, simulation, and infrastructure. We move fast, ship to real robots, and open-source everything we can. If you want your work to matter beyond a paper or a demo, this is the place.
The Role
The hard problem in simulation is not building a demo environment. It is building digital twins that are faithful enough to train policies, close sim-to-real gaps, and accelerate hardware development at scale. As a Software Engineer, Digital Twin, you will own the environments, tooling, and pipelines that make Asimov's virtual counterpart a first-class engineering asset. You will work across MuJoCo, Isaac Sim, and Unreal Engine -- using the right tool for the right layer of the stack, from physics training to photorealistic synthetic data generation.
What You Will Do
Build and maintain high-fidelity digital twin environments for Asimov across MuJoCo, Isaac Sim, and Unreal Engine, calibrated to real hardware behavior.
Design and own the systems -- not just the environments -- that let locomotion, autonomy, and perception teams generate, validate, and iterate on simulation scenarios at scale.
Build pipelines for asset import, USD and MJCF workflows, sensor modeling, and real-to-sim calibration to keep digital twins synchronized with evolving hardware.
Develop photorealistic rendering pipelines in Unreal Engine for synthetic data generation and perception model training.
Work with hardware and mechatronics teams to model actuator dynamics, contact physics, and structural behavior, ensuring simulation parameters reflect physical ground truth.
Integrate digital twin environments with Menlo 's locomotion training pipeline (Cyclotron) and autonomy stack, enabling teams to run experiments and close the sim-to-real gap.
Contribute to the open-source Asimov simulation stack, including tooling, documentation, and reproducible environment workflows.
What You Will Bring
Hands-on experience building or maintaining simulation environments in MuJoCo, Isaac Sim, or a comparable physics engine -- on real robot development programs, not just coursework.
Proficiency in Python and C++.
Solid understanding of rigid body dynamics, contact simulation, and how simulator parameters translate to physical hardware behavior.
Experience building the systems that enable simulation at scale: procedural generators, validation pipelines, CI hooks, or environment tooling.
Familiarity with ROS2 and common robotics data formats.
Nice to Have
Unreal Engine
Posted June 18, 2026