Computer Vision Engineer (Autonomous Driving)

42dot의 Computer Vision Engineer는 안전한 Autonomous Driving 기술 구현을 위한 핵심 Computer Vision 및 Machine Learning 기술을 연구하고 개발합니다. 자율주행 차량에서 수집되는 다양한 센서 데이터를 기반으로 3D 환경을 이해하고, 사람 수준의 인지 성능을 구현하기 위한 알고리즘을 개발합니다. 또한 최신 Computer Vision 기술과 AI 모델을 활용하여 Perception 성능을 고도화하고, 차세대 Autonomous Driving System 개발에 기여합니다.

As a Computer Vision Engineer at 42dot, you will focus on researching and developing advanced computer vision and machine learning technologies for autonomous driving. You will develop algorithms that enable human-level perception by understanding 3D environments from multi-modal sensor data collected by autonomous vehicles. Working with state-of-the-art vision and AI technologies, you will contribute to the next generation of autonomous driving systems.

Responsibilities

• 자율주행을 위한 3D Computer Vision 및 Machine Learning 알고리즘 연구 및 개발
• 3D Shape Modeling, Object Pose Estimation, Tracking 등 3차원 인지 알고리즘 개발
• 대규모 비정형 데이터 기반 Self-supervised Representation Learning 연구
• World Model 및 Closed-loop Simulation 기반 Autonomous Driving 기술 연구
• Vision, Robotics 및 Physics-based Vision 기술 연구 및 개발
• 고성능·대규모 Vision System 설계 및 최적화
• Conduct research and develop 3D computer vision and machine learning algorithms for autonomous driving
• Develop 3D shape modeling, object pose estimation, and tracking algorithms
• Research self-supervised representation learning using large-scale unlabeled scene data
• Develop world models and closed-loop simulation technologies for autonomous driving
• Explore advanced vision, robotics, and physics-based vision algorithms
• Design efficient and scalable computer vision systems

• Computer Vision, Robotics, Machine Learning 또는 관련 분야 석사 이상 또는 이에 준하는 실무 경험
• 관련 분야 2년 이상의 연구 또는 개발 경력
• Computer Vision 및 Machine Learning 알고리즘에 대한 이론 및 실무 지식
• Python, C/C++ 기반 개발 역량
• Master's or Ph.D. in Computer Vision, Robotics, Machine Learning, or a related field, or equivalent practical experience
• 2+ years of relevant research or industry experience
• Strong theoretical and practical knowledge of computer vision and machine learning
• Proficiency in Python and C/C++

• Autonomous Driving, Robotics 또는 3D Vision 관련 프로젝트 수행 경험
• GPS, IMU, Camera, LiDAR 등 Multi-sensor Data Processing 및 Sensor Fusion 경험
• SLAM, Depth Estimation, 3D Reconstruction, Pose Estimation 알고리즘 개발 경험
• CUDA, OpenCL 등 병렬 프로그래밍 및 시스템 최적화 경험
• VR/AR Application 개발 경험
• CVPR, ICCV, ECCV, TPAMI, IJCV 등 Top-tier 학회 또는 저널 논문 게재 경험
• 대규모 Cloud 환경에서 ML Model 개발 및 운영 경험
• Proven experience in autonomous driving, robotics, or 3D vision projects
• Hands-on experience with multi-sensor data processing and sensor fusion using GPS, IMU, cameras, and LiDAR
• Experience developing SLAM, depth estimation, 3D reconstruction, or pose estimation algorithms
• Experience with parallel programming technologies such as CUDA or OpenCL and system optimization
• Experience developing VR/AR applications
• Publication record in top-tier conferences or journals such as CVPR, ICCV, ECCV, TPAMI, or IJCV
• Experience deploying and managing machine learning models in large-scale cloud environments

How to work in 42dot, About 42dot Way →