• Applied AI & R&D: Leading applied AI research and development projects focusing on precision agriculture, smart industry, and advanced computer vision solutions.
• Industry Solutions: Architecting and executing technology transfer projects bridging academic research with industrial manufacturing and agricultural production lines.

• Technical Leadership: Managed the Edge AI and Computer Vision team, defining R&D architectures and strategies in Precision Agriculture.
• LLMs & GenAI: Experience in development, fine-tuning, and deployment of LLMs for automation agents and customer intelligence.
• Electronic Traps Project:
  • Managed project and developed embedded software and AI cloud infrastructure (AWS Lambda, S3, RDS) for pest counting.
  • Concept and validation of IoT hardware/software architecture from design to homologation.
  • Generated insights on infestation and climate, optimizing pesticide application (Operational KPIs).
• Edge AI Projects:
  • Developed stereo vision system (ZED Camera) for real-time coffee volume calculation on harvesters.
  • Optimized and deployed Deep Learning models on NVIDIA Jetson modules for weed identification and selective spraying (DeepStream SDK), reducing costs and inputs.
• Image Processing (Cloud - Drone/Satellite):
  • Implemented large-scale Deep Learning algorithms for weed identification using PySpark for distributed image processing.
  • Generated application maps and agronomic insights from aerial imagery.
• Built and maintained data pipelines and MLOps (Python, PySpark, Docker, Git), ensuring data quality and scalability.
• Mentored developers using Agile methodologies (SCRUM, Kanban).

• Structured and taught postgraduate modules in AI, focusing on industrial applications of Computer Vision and Deep Learning.

• Worked in a software company focused on security and vehicle tracking solutions based on IoT devices.
• Responsible for the technical interface with clients, bridging the gap between commercial/functional needs and technical software delivery.

• Direct involvement in academic R&D, focusing on developing and validating Machine Learning (ML) and Deep Learning (DL) algorithms for Agritech applications.
• Created models for disease/pest identification and weed eradication.

Focus: Artificial Intelligence and Digital Twins.

Thesis: Deep Neural Networks with Weight Reduction for Low-Cost Hardware Applied to Invasive Species Identification in Cultivars.

Dissertation: Weed classification in image databases using convolutional neural networks.