Physical AI Engineer

42dot
South Korea
Workplace: HybridFull timeFunction: Data Science & Machine LearningEducation: mastersSkills: []

Develop end-to-end trajectory generation and decision-making models for autonomous driving, bridging generative AI with real-world robotic and mobility actuation. Build and optimize Model-Based Reinforcement Learning and Imitation Learning approaches, integrate motion planning, filtering, and navigation algorithms, and support CUDA-based on-device performance for real-time execution. Validate models in both simulation and real vehicle environments while collaborating with perception, planning, and control teams.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
42dot
42dot
1 month ago

Physical AI Engineer

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 19 hours agoStatus: Live

Job Summary

Develop end-to-end trajectory generation and decision-making models for autonomous driving, bridging generative AI with real-world robotic and mobility actuation. Build and optimize Model-Based Reinforcement Learning and Imitation Learning approaches, integrate motion planning, filtering, and navigation algorithms, and support CUDA-based on-device performance for real-time execution. Validate models in both simulation and real vehicle environments while collaborating with perception, planning, and control teams.
Location: South Korea
Workplace: Hybrid
Employment Type: Full time
Job Function: Data Science & Machine Learning

Key Responsibilities

  • •Develop data preprocessing pipelines, train models, and run performance validation for end-to-end trajectory generation and decision-making models.
  • •Develop and optimize Model-Based Reinforcement Learning (MBRL) and Imitation Learning (IL) algorithms.
  • •Integrate and validate motion planning, filtering (e.g., Kalman Filter, Particle Filter), and navigation algorithms.
  • •Support CUDA-based optimization of deep learning models and planning pipelines to achieve on-device real-time performance.
  • •Collaborate with perception, planning, and control teams and validate approaches in simulation and real-world vehicle environments.

Key Requirements

  • •Master’s degree or higher in Computer Science, Electrical Engineering, Robotics, Aerospace Engineering, or related STEM field (or equivalent practical experience).
  • •Hands-on experience building and training AI models using Python with modern deep learning frameworks such as PyTorch or JAX.
  • •Theoretical and practical understanding of motion planning, filtering, and navigation algorithms, including implementation experience.
  • •Experience validating AI models and algorithms in simulation environments or on real hardware systems.
  • •Strong understanding of machine learning, deep learning, and reinforcement learning concepts.
Experience:Autonomous drivingRoboticsComputer vision
Education:Master's
Tech Stack:PythonPyTorchJAXCUDAC++TensorRTKalman FilterParticle Filter

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