Summary
Carlos Marañes is a Machine Learning Engineer specializing in computer vision and 3D vision, with eight years of experience delivering end-to-end AI solutions from synthetic data generation to production deployment. He has a strong track record in industry and research—most notably a livestock weight estimation system that cut manual processing time by 90% and practical reconstruction and defect-detection systems for construction. Comfortable working under strict hardware and latency constraints, he combines robotics, graphics and vision expertise with hands-on skills in Python, PyTorch, OpenCV and modern architectures like transformers and CNNs. Carlos leverages virtual environments such as Unity and Roblox to generate training data and is actively exploring multimodal and generative AI using LLM ecosystems like Hugging Face, Ollama and OpenAI. Based in Zaragoza, Spain, he also teaches deep learning for computer vision and brings a pragmatic research mindset from a Master’s in Robotics, Graphics and Computer Vision.
8 years of coding experience
5 years of employment as a software developer
Master Program in Robotics, Graphics and Computer Vision, Computer Science, Master Program in Robotics, Graphics and Computer Vision, Computer Science at Universidad de Zaragoza
Computer Science (Master of Science) - Erasmus, Computer Science (Master of Science) - Erasmus at The University of Freiburg
English, Spanish