Computer Vision Engineer

About the job

Edison Smart are searching for a Senior Computer Vision & AI Engineer to lead the development and deployment of advanced vision-based perception systems for autonomous inspection robots. This is a hands-on role focused on building, optimising, and deploying deep learning models across multi-modal sensor stacks in real-world robotic environments.

This is a fully remote contract opportunity, offering €80--100 per hour, for an initial 6-month engagement.

Key Responsibilities

• Develop and deploy vision-based perception algorithms using deep learning and machine vision techniques (CNNs, ViTs, DETR-based models)
• Design and implement supervised, self-supervised, and unsupervised learning methods for multi-modal data (RGB, LiDAR, thermal, etc.)
• Build and optimise models for:
  • 2D & 3D object detection and tracking
  • Anomaly detection
  • LiDAR-based semantic segmentation and 3D point cloud understanding
• Optimise models for edge deployment (quantisation, pruning, distillation) and deploy on NVIDIA Jetson platforms (Xavier, Orin, Thor)
• Integrate perception pipelines into robotic systems using ROS1/ROS2
• Support and maintain MLOps workflows, ensuring reproducible training, evaluation, and CI/CD processes
• Contribute to AWS-based AI pipelines (SageMaker, Bedrock, Lambda, S3) for scalable training and model lifecycle management
• Drive research and innovation in multi-modal and 3D representations (Gaussian Splatting, NeRF, OpenCLIP embeddings)
• Collaborate cross-functionally with robotics, software, and AI teams to improve autonomy, semantic mapping, and mission planning capabilities

Required Experience

• Degree in Computer Science, Robotics, or a related technical field
• 2 years' professional experience in computer vision, deep learning, or robotic perception
• Strong understanding of Vision Transformers (ViTs), CNNs, and DETR-based object detection architectures
• Hands-on experience with PyTorch, OpenCV, MMDetection and/or Detectron2
• Practical experience in model optimisation and deployment using TensorRT, ONNX, Docker, and/or NVIDIA DeepStream
• Experience with data annotation tools such as CVAT, Label Studio, or 3D Point Labeler
• Exposure to versioning and MLOps tools including GitLab CI/CD, MLflow, n8n, AWS SageMaker, and/or Bedrock
• Strong programming skills in Python, C++, and Bash
• Proven ability to work independently in fast-paced environments while collaborating effectively across teams
• Fluent in English (German Desired)

Engagement Details

• Contract position
• €80--100 per hour
• Fully remote
• Initial 6-month engagement with potential extension
• High-impact role on cutting-edge autonomous robotics programme