We are looking for the best
AD Division의 Physical AI Engineer (Model)는 Generative AI 기술을 실제 로봇 및 모빌리티 시스템의 의사결정과 제어로 연결하는 역할을 수행합니다. 차세대 End-to-End Trajectory Generation 및 Decision-making Model 개발에 참여하며, 복잡하고 동적인 환경에서도 안전하고 효율적인 주행이 가능한 Physical AI 시스템을 구축합니다. 또한 Reinforcement Learning(RL), Imitation Learning(IL), Motion Planning 기술을 융합하여 Autonomous Driving AI의 성능을 향상시키고 실제 차량 환경에 적용 가능한 모델을 개발합니다.
The Physical AI Engineer (Model) in the AD Division bridges generative AI technologies with real-world robotic and mobility actuation systems. This role focuses on developing next-generation end-to-end trajectory generation and decision-making models capable of safe and efficient operation in complex and dynamic environments. You will integrate reinforcement learning, imitation learning, and advanced motion planning techniques to improve autonomous driving AI performance and deploy scalable physical AI solutions.
Responsibilities
- End-to-End Trajectory Generation 및 Decision-making Model 개발을 위한 데이터 전처리, 모델 학습 및 성능 검증 수행
- Model-Based Reinforcement Learning(MBRL) 및 Imitation Learning(IL) 알고리즘 개발 및 최적화
- Motion Planning, Filtering(Kalman Filter, Particle Filter 등), Navigation 알고리즘 통합 및 검증
- CUDA 기반 딥러닝 모델 및 Planning Pipeline 최적화를 통한 On-device Real-time 성능 확보 지원
- Simulation 및 실제 차량 환경에서 AI 모델 및 알고리즘 검증 수행
- Perception, Planning, Control 팀과 협업하여 차세대 Physical AI 시스템 개발
- Develop data preprocessing pipelines, train models, and conduct 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 on-device optimization of deep learning models and planning pipelines using CUDA to achieve real-time performance
- Validate AI models and algorithms in simulation and real-world vehicle environments
- Collaborate with perception, planning, and control teams to develop next-generation physical AI systems
Qualifications
- 컴퓨터공학, 전자공학, 로봇공학, 항공우주공학 또는 관련 분야 석사 학위 이상 또는 이에 준하는 실무 경험
- Python 및 최신 딥러닝 프레임워크(PyTorch, JAX)를 활용한 AI 모델 개발 및 학습 경험
- Motion Planning, Filtering, Navigation 알고리즘에 대한 이론적 이해 및 구현 경험
- Simulation 또는 실제 Hardware 환경에서 AI 모델 및 알고리즘 검증 경험
- 머신러닝, 딥러닝 및 강화학습에 대한 이해
- Master’s degree or higher in Computer Science, Electrical Engineering, Robotics, Aerospace Engineering, or a related STEM field, or equivalent practical experience
- Hands-on experience developing and training AI models using Python and modern deep learning frameworks such as PyTorch or JAX
- Strong theoretical and practical understanding of motion planning, filtering, and navigation algorithms
- 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
Preferred Qualifications
- ICRA, IROS, CVPR, NeurIPS, RSS 등 Robotics 및 Computer Vision 분야 Top-tier 학회 또는 저널 논문 게재 경험
- C++, CUDA, TensorRT 기반 고성능 연산 및 추론 최적화 경험
- End-to-End Trajectory Generation 또는 Generative AI 기반 Motion Planning 프로젝트 경험
- Reinforcement Learning(RL) 또는 대규모 Imitation Learning(IL) 데이터셋 구축 및 Training Pipeline 운영 경험
- Autonomous Driving 또는 Robotics 분야 AI 모델 개발 경험
- 대규모 AI 학습 및 추론 시스템 구축 경험
- Publication record in top-tier robotics and computer vision conferences or journals such as ICRA, IROS, CVPR, NeurIPS, or RSS
- Experience with high-performance computing and inference acceleration using C++, CUDA, and TensorRT
- Experience developing end-to-end trajectory generation models or generative AI-based motion planning systems
- Experience building datasets and operating training pipelines for reinforcement learning or large-scale imitation learning
- Experience developing AI models for autonomous driving or robotics applications
- Experience building large-scale AI training and inference systems
