AI/ML Research Engineer, Additive Manufacturing (KTP Associate)

This full-time post is a Knowledge Transfer Partnership Associate role between the Centre for Additive Layer Manufacturing (CALM) at the University of Exeter and Rapid Fusion. The role is available immediately for 36 months. The role will be physically based with Rapid Fusion Ltd (part of the EVO 3D group) at their premises in Skypark, Exeter with regular travel to the University. The KTP will develop software for intelligent process control in Large Format Additive Manufacturing (LFAM), focused on improving polymer deposition consistency and interlayer bonding performance. The candidate is expected to have a good understanding of the LFAM process including thermal behaviour of the polymers and knowledge of polymer material science.

Duties & Responsibilities

• To work in collaboration with an Industry and Academic Supervisor to successfully deliver the following KTP Project: Leading the development of AI-enabled software for intelligent process control in Large Format Additive Manufacturing (LFAM), focused on improving polymer deposition consistency and inter-layer bonding performance.
• To actively contribute to the University of Exeter’s research activity through applying latest thinking to industrial challenges
• To transfer the latest academic thinking relative to the project into the company partner.

To develop AI-enabled software that improves the reliability and strength of Large Format Additive Manufacturing systems for Rapid Fusion. The project will enable higher-value product sales, software licensing, and new services, while reducing waste and supporting wider industrial adoption of large-scale polymer 3D printing.

The KTP Associate will be embedded within Rapid Fusion Ltd (RF), to deliver the project objectives by:

• Lead the development of AI-enabled software for intelligent process control in Large Format Additive Manufacturing (LFAM) focused on improving polymer deposition consistency and inter-layer bonding performance.
• Investigate and model polymer flow, thermal behaviour and inter-layer bonding to improve print quality and mechanical performance.
• Design and implement data-driven, adaptive control algorithms to optimise LFAM process parameters in real time.
• Integrate sensor data into AI models to predict print quality, bonding performance and defect formation.
• Validate models using materials characterisation and process data.
• Translate research outputs into robust, deployable software tools for Rapid Fusion Ltd LFAM systems.
• Work closely with company engineers to embed new knowledge and capabilities into manufacturing workflows.
• Contribute to knowledge transfer, documentation and reporting in line with Innovate UK KTP requirements.

This project will enable Rapid Fusion Ltd to improve current processes and to enable future innovations and products to accelerate its strategic goals.