Toni is the co-founder and CSO of Aizon, a cloud company that provides an AI SaaS platform for the Biotech and Pharma industry. He is member of the PDA Regulatory Affairs and Quality Advisory Board and co-chair of the Advanced Manufacturing and Applied Process Digitalization PDA Interest Group. Toni teaches AI subjects at the university URV and OBS, and SME for the United Nations in AI subjects in Life Sciences. He has written numerous articles in the Pharma field and holds a dozen international patents related to the encryption, transmission, storage and processing of large volumes of data for regulated environments in the cloud. Toni is Physicist, PhD, and Master in Information and Knowledge Society and post graduated in quality systems for manufacturing and research pharmaceutical processes.
The industrialization of AI in drug manufacturing is a critical step toward achieving scalable, efficient, and compliant production processes. While AI has demonstrated its potential in predictive quality control, process optimization, and deviation reduction, the challenge lies in scaling AI models beyond pilot projects and ensuring seamless integration within regulated environments, like drug manufacturing.
Key barriers to AI industrialization include fragmented data ecosystems, lack of standardized model formats, and regulatory concerns around AI validation and lifecycle management. A major enabler for overcoming these challenges is the adoption of open and scalable AI model formats, such as ONNX (Open Neural Network Exchange), which allows AI models to be deployed across different platforms and hardware without requiring complex reengineering. By leveraging ONNX and model compression techniques, pharmaceutical manufacturers can efficiently scale AI applications from research environments to industrial production, ensuring compatibility with existing manufacturing execution systems and real-time process control architectures.
The relevance of this topic is critical as AI adoption accelerates in Good Manufacturing Practices (GMP) operations. Without scalable deployment strategies, AI remains confined to isolated use cases, limiting its transformative impact. By leveraging ONNX and cloud-based AI model deployment, pharmaceutical companies can unlock AI’s full potential, enabling real-time, AI-driven decision-making at an industrial scale while ensuring regulatory compliance.
This session will provide attendees with a roadmap for AI scalability, covering best practices for deploying AI in large-scale production environments, optimizing model inference performance, and ensuring AI models remain adaptable to dynamic manufacturing conditions.
