Computer Vision & AI Engineer

• Develop and deploy vision-based perception algorithms for autonomous inspection robots using deep learning and machine vision techniques, including CNN- and ViT-based architectures.
• Design and implement supervised, self-supervised, and unsupervised learning methods for multi-modal data (RGB, LiDAR, thermal, etc.).
• Build and optimize models for:

• Object detection and tracking (2D & 3D)
• Anomaly detection
• LiDAR-based semantic segmentation and 3D point cloud understanding

• Optimize models for on-device inference (quantization, pruning, distillation) and deploy them on edge hardware (NVIDIA Jetson Xavier/Orin/Thor, etc.).
• Integrate perception pipelines into robotic systems via ROS1/ROS2 and collaborate closely with software and robotics teams.
• Support MLOps workflows, ensuring reproducible training, evaluation, and CI/CD for AI models.
• Support and maintain cloud-based AI pipelines on AWS (SageMaker, Bedrock, Lambda, S3) for scalable training, inference, and model lifecycle management.
• Contribute to research on multi-modal and 3D representations (Gaussian Splatting, NeRF, OpenCLIP-based embeddings).
• Participate in continuous improvement of our AI infrastructure for mission planning, semantic mapping, and robot autonomy.

• Degree in Computer Science, Robotics, or a related technical field.
• 2+ years of professional experience in computer vision, deep learning, or robot perception.
• Strong understanding of Vision Transformers (ViTs), Convolutional Neural Networks (CNNs), and DETR-based models for object detection.
• Hands on experience with Frameworks including PyTorch, OpenCV, MMDetection, and/or Detectron2.
• Applied experience in Optimization & Deployment with TensorRT, ONNX, Docker, and/or NVIDIA DeepStream.
• Direct experience with Data Annotation using CVAT, and/or Label Studio, and/or 3D Point Labeler.
• Practical experience in Versioning & MLOps using GitLab CI/CD, MLflow, n8n, AWS SageMaker, and/or Bedrock.
• Strong programming skills in Python, C++, Bash.
• Strong analytical, problem-solving, and growth mindset.
• Excellent collaboration between cross-functional AI and robotics teams.
• Passion for innovation, autonomy, and pushing the boundaries of perception systems.
• Ability to work independently and manage multiple priorities in a fast-paced environment.
• Fluent in English., * Experience with LLMs, VLMs, VLAs and multi-modal embeddings.
• Familiarity with semantic scene graphs-based 3D Gaussian splatting.
• Exposure to cloud-based data services or AI workflow orchestration.
• Contributions to open-source projects in AI/robotics or publications in the field.
• Residing within ±2 hours of the CET time zone and available to travel to Darmstadt for three days every six weeks for onsite team meetings. All travel costs will be covered by the company.

Korial is the Enterprise AI Platform for the autonomous industrial future. From our roots in the labs of TU Darmstadt, we have grown into a team of over 100 people building the intelligence layer that orchestrates autonomous inspections across infrastructure worldwide. Our platform unifies data, missions, and mixed fleets of robots and devices so operators can supervise assets from a single source of truth instead of walking every round on foot. We work at the intersection of AI, robotics, and industrial operations, turning noisy real-world telemetry into dependable, actionable insight for customers on five continents. Our team brings together more than 30 nationalities and deep experience in software engineering, robotics, cloud infrastructure, and enterprise operations - including 11 PhDs leading core product development since 2019. You must create an Indeed account before continuing to the company website to apply