Computer Vision Engineer

Develop proof-of-concept (POC) computer vision systems for intelligent mobility and in-vehicle applications. The role focuses on rapidly evaluating, implementing, and deploying state-of-the-art computer vision and AI technologies on vehicle-grade edge computing platforms, bridging cutting‑edge research and real‑world intelligent mobility systems. Responsibilities Develop proof-of-concept systems using state-of-the-art AI and computer vision technologies. Design and implement computer vision algorithms for object detection, tracking, semantic/instance segmentation, 3D scene understanding, visual localization, mapping, driver and occupant monitoring, and behavior recognition. Build solutions using modern AI approaches including Vision Transformers (ViT), Vision‑Language Models (VLMs), Multimodal AI, Foundation Models, Self‑Supervised Learning, and Generative AI. Evaluate and adapt the latest research papers and open‑source models to automotive and intelligent mobility applications. Integrate camera, vehicle, and sensor data to create innovative AI‑driven applications. Develop and integrate AI software on embedded and edge computing platforms for in‑vehicle applications. Design real‑time perception systems operating under vehicle constraints including compute, memory, latency, power consumption, and robustness. Optimize AI models for deployment on automotive SoCs, GPUs, and AI accelerators. Prototype and evaluate end‑to‑end systems on vehicle platforms, embedded devices, and research vehicles. Develop software for deployment and demonstration in vehicle‑based proof‑of‑concept platforms. Evaluate tradeoffs among accuracy, latency, memory footprint, and operational robustness. Collaborate with researchers, software engineers, and system engineers to realize innovative concepts and demonstrations. Stay up to date with emerging trends in computer vision, multimodal AI, edge AI, and intelligent mobility systems. Qualifications Required Qualifications Master's degree or higher in Computer Science, Electrical Engineering, Robotics, Artificial Intelligence, or a related field. Strong background in Computer Vision and Machine Learning. Hands‑on experience with PyTorch, TensorFlow, OpenCV, or similar frameworks. Experience implementing and training deep learning models including CNNs, Transformers, Vision Transformers (ViT), Vision‑Language Models (VLMs), and multimodal architectures. Strong programming skills in Python and C++. Experience reading, reproducing, and extending recent AI/CV research publications. Familiarity with Linux development environments. Excellent verbal and written communication skills. Preferred Qualifications Experience with Foundation Models, Large Vision Models, and Multimodal AI systems. Experience with CLIP, SAM (Segment Anything), DINOv2, BEV‑based perception models, or similar state‑of‑the‑art vision technologies. Experience with Generative AI and synthetic data generation. Experience developing software on embedded Linux systems. Experience with CUDA, TensorRT, ONNX Runtime, OpenVINO, or comparable inference optimization frameworks. Experience optimizing and deploying AI models on edge devices and automotive computing platforms. Experience with NVIDIA Jetson, NVIDIA DRIVE, Qualcomm Snapdragon Ride, or similar embedded AI platforms. Experience with ROS/ROS2, sensor fusion, or robotic/automotive systems. Publications in leading AI, robotics, or computer vision conferences are a plus. #J-18808-Ljbffr