Senior Physical AI Engineer

42dot
South Korea
Workplace: HybridFull timeFunction: Data Science & Machine LearningExperience: 5+ yearsEducation: mastersSkills: ["Collaboration","Research and development","Problem-solving"]

Build high-fidelity, physics-based simulation environments to train and validate autonomous driving AI agents. Leverage 3D generative AI (including 3D Gaussian Splatting) and vehicle dynamics models to reduce the Sim-to-Real gap, and develop scalable closed-loop testing pipelines. Implement and optimize high-performance simulation modules using C++, Python, and CUDA, integrating perception, planning, and control algorithms to improve simulation fidelity and accelerate model development and deployment.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
42dot
42dot
1 month ago

Senior Physical AI Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 11 hours agoStatus: Live

Job Summary

Build high-fidelity, physics-based simulation environments to train and validate autonomous driving AI agents. Leverage 3D generative AI (including 3D Gaussian Splatting) and vehicle dynamics models to reduce the Sim-to-Real gap, and develop scalable closed-loop testing pipelines. Implement and optimize high-performance simulation modules using C++, Python, and CUDA, integrating perception, planning, and control algorithms to improve simulation fidelity and accelerate model development and deployment.
Location: South Korea
Workplace: Hybrid
Employment Type: Full time
Job Function: Data Science & Machine Learning
Seniority: Mid level

Key Responsibilities

  • •Reconstruct high-fidelity 3D environments using 3D Gaussian Splatting (3DGS) and generative AI technologies.
  • •Design and develop scalable simulation pipelines for closed-loop testing of AI models.
  • •Implement and validate physics-based vehicle dynamics and kinematics models.
  • •Develop and optimize high-performance simulation modules using C++, Python, and CUDA.
  • •Integrate perception, planning, and control algorithms into simulation environments to improve fidelity and reduce the Sim-to-Real gap.

Key Requirements

  • •Master’s degree or higher in Computer Science, Robotics, or a related field with 5+ years of professional experience (or equivalent industry experience).
  • •Strong production software development using Modern C++ and Python.
  • •Deep understanding of vehicle dynamics and kinematics with strong mathematical modeling skills.
  • •3+ years integrating simulation systems using physics engines/simulators such as Isaac Sim, MuJoCo, or CARLA.
  • •Experience designing and developing large-scale simulation systems.
Experience:5+ yearsAutonomous drivingRoboticsSimulationClosed-loop testingSim-to-Real
Education:Master's in Computer Science, Robotics, or a related field
Skills:CollaborationResearch and developmentProblem-solving
Tech Stack:C++PythonCUDA3D Gaussian Splatting (3DGS)NeRFIsaac SimMuJoCoCARLA

Company Brief

42dot
Develops autonomous driving and mobility software platforms, including AI-based perception, mapping, routing, and connected-vehicle technologies. It works on next-generation transportation systems and self-driving vehicle capabilities for automotive applications.
Industry: Autonomous Vehicles
Company Size: Large (251 to 1,000 employees)
Growth: Scaleup
Headquarters: Seoul, South Korea
Founded: 2019
WebsiteLinkedIn