1 year ago
Responsibilities
- Design and develop simulation environments for robotics training and evaluation.
- Build systems supporting perception, navigation, manipulation, embodied AI, synthetic data generation, and robot learning.
- Model and calibrate robot dynamics, sensors, contacts, physics, and environmental interactions for sim-to-real transfer.
- Develop production-quality simulation tools, pipelines, benchmarks, and infrastructure for reliable and scalable execution.
- Optimize simulation performance while maintaining physical realism.
- Collaborate with robotics, machine learning, AI, world-model, and research teams.
Requirements
- Experience building robotics simulation systems for robotics, autonomy, embodied AI, or physical AI.
- Experience with robotics simulators such as Isaac Sim, MuJoCo, PyBullet, Gazebo, Drake, or equivalent.
- Understanding of robot dynamics, physics simulation, sensor modeling, and sim-to-real transfer.
- Strong software engineering skills in Python, C++, or similar languages.
- Experience building production-quality simulation software and infrastructure.
- Experience writing reliable, maintainable, and well-tested code.
- Strong systems thinking, problem-solving skills, and ability to collaborate with robotics, machine learning, and research teams.
- Preferred: experience with NVIDIA Isaac Sim, Omniverse, synthetic data generation, domain randomization, procedural environment generation, ROS2, GPU-accelerated simulation, or simulation performance optimization.
- An MS or PhD in Robotics, Computer Science, Mechanical Engineering, or a related field is preferred.
Benefits
- On-site, in-person work in San Francisco.
- Opportunity to build foundational simulation infrastructure for robotics, embodied AI, world models, and physical AI.
About Moonlake
Moonlake builds interactive world models and simulation infrastructure that generate, simulate, and reason over 3D environments for embodied AI, robotics, and gaming. Its platform and APIs let researchers and developers create assets, scenes, and digital twins at scale, and interact with them via natural language and multimodal inputs. The company is privately held, founded in 2025, headquartered in San Francisco, and raised a $28M seed round in 2025.