Research Engineer Contractor: Robotics & 3D Simulation

Job Number: P25T09

About the role

Honda Research Institute USA (HRI-US) is seeking a self-motivated research engineer to join our Intelligent Robotics Research division. This individual will support research workflows by preparing and running high-fidelity 3D simulation experiments in robotics, including but not limited to: reconstructing real-world objects and contact-rich scenes, aligning/evaluating simulated behavior with real-world measurements, adapting/evaluating existing machine learning and control methods using simulation. The role combines hands-on scene creation, robotics simulation, simulation-based methods, experimental validation, and clear communication of technical and implementation outcomes. San Jose, CA

Responsibilities

• Create diverse contact-rich scenes in simulation using 3D scanners and/or 3D modelling of real-world objects.
• Perform system identification to reduce/evaluate sim-to-real gaps.
• Create and run scenes across different simulators to compare and evaluate simulation fidelity.
• Implement, adapt, and evaluate existing methods that are relevant to and leverage simulation (e.g., control optimization, 3D representation learning).
• Deliver results in accordance with project timelines.
• Prepare written and oral technical reports and demonstrations.
• Collaborate with our teams of scientists and engineers in Honda’s regional and global R&D offices.
• Communicate results, tradeoffs, and implementation outcomes.

Requirements

• MS or PhD in Robotics, Computer Science, or related field.
• Experience with 3D asset creation or processing workflows, such as 3D scanning, mesh cleanup, CAD/Blender-style modeling, material definition, etc.
• Experience with creating high-fidelity 3D scenes and 3D assets of real objects.
• Experience with running robotics simulation (experience with multiple platforms preferred).
• Comfortable reading, understanding, and implementing algorithms from research papers.
• Has general knowledge/experience with machine learning (e.g., collecting data, training and evaluating models, defining loss, understanding of different architectures).

Qualifications

• Experience with contact-rich physics simulation.
• Experience with 3D representation learning.
• Has knowledge and experience on system identification.
• Has general knowledge/experience with control optimization (e.g., multi-chain gradients and Jacobians, optimization steps and trust regions).
• Familiarity with numerical simulation, optimization, or differentiable physics workflows.
• Demonstrated expertise through research, projects, or open-source contributions.