Job Description:
Job Overview
We are looking for a Research Engineer to build simulation environments, training workflows, and evaluation systems for embodied AI and robotics.
You will help create the virtual environments and tools that enable robotic policies to be trained, tested, and evaluated at scale before being deployed in the real world. Depending on your expertise, you may focus on simulation-based policy training and evaluation, or on scene reconstruction and synthetic data generation.
This role is ideal for an engineer with strong simulation or robotics experience who enjoys building technically grounded environments that support real learning and measurable improvements in robotic performance.
What You Will Own
Build and maintain simulation environments for robot learning, training, and evaluation.
Develop robotic tasks, environments, reward functions, and evaluation metrics.
Work with platforms such as NVIDIA Isaac Sim, Isaac Lab, MuJoCo, or similar simulation frameworks.
Support simulation-based policy training and automated evaluation at scale.
Implement domain randomization and other techniques to improve policy robustness and sim-to-real transfer.
Develop sensor simulation, synthetic data generation, or scene reconstruction workflows as relevant to your specialization.
Validate simulation results against real-world robot behavior and investigate discrepancies.
Build reusable simulation tools and pipelines that improve experiment reproducibility and research efficiency.
Required Qualifications
Experience in robotics simulation, robotics research, simulation-based training, or a related technical field.
Strong Python programming skills and familiarity with relevant robotics or simulation tools.
Experience with at least one simulation platform, such as Isaac Sim, Isaac Lab, MuJoCo, or an equivalent framework.
Understanding of robotic systems, 3D environments, physics simulation, or learning-based robotics.
Experience building functional simulation environments, training workflows, evaluation pipelines, or synthetic data systems.
Strong debugging and experimental skills, with the ability to validate whether simulation results reflect meaningful real-world behavior.
Preferred Qualifications
Experience training or evaluating robotic policies in simulation.
Experience with domain randomization, sim-to-real transfer, or sensor simulation.
Experience with scene reconstruction, synthetic data generation, or physically grounded 3D environment creation.
Experience building reusable tools for large-scale simulation or automated evaluation.
Experience comparing simulation results with real-world robot performance.
Note: Candidates may specialize in either simulation-based policy training and evaluation or scene reconstruction and synthetic data generation. Experience across both areas is not required. However, candidates should demonstrate technical depth beyond visual scene creation alone.
Default Benefits:
Health insurance
Vision care
Dental coverage
401(k)
Paid holidays
PTO (Paid Time Off)
Sick leave