Machine Learning Engineer for Ship Design & Hydrodynamics (KTP Associate)
Develop physics-informed AI tools for ship design optimization in a Knowledge Transfer Partnership with Compute Maritime Ltd.
Best for:Best for engineers with expertise in machine learning, computational fluid dynamics, and ship hydrodynamics who are eager to apply research to commercial AI-driven design tools.
Overview
This role is a **Knowledge Transfer Partnership (KTP)** between the University of Southampton and **Compute Maritime Ltd**, a London-based deep-tech company specializing in AI-driven ship design. The successful candidate will bridge research and industry by embedding generative AI and computational fluid dynamics (CFD) into NeuralShipper, a proprietary platform for end-to-end vessel lifecycle optimization. The position focuses on translating academic expertise into scalable commercial solutions, including physics-informed modeling, design optimization, and integration of wind-assisted propulsion systems. It is ideal for engineers with a strong background in machine learning, hydrodynamics, and engineering simulation tools, seeking to contribute to both research and industry innovation.
What you'll do
- Translate academic research into commercially viable AI tools by managing work packages for NeuralShipper’s integration into ship design workflows.
- Develop and validate fast, physics-informed models for predicting ship resistance, propulsion performance, and energy efficiency using CFD and benchmark datasets.
- Design and implement multidisciplinary optimization methods, integrating them into NeuralShipper for automated vessel design improvements.
- Extend NeuralShipper’s capabilities to wind-assisted propulsion and rigid sail systems, collaborating with industry stakeholders for practical validation.
- Collaborate between the University of Southampton and Compute Maritime Ltd to embed research into scalable, industry-ready software solutions.
Requirements
Degree required: Master’s degree (MSc/MEng) in Machine Learning, AI, Computational Fluid Dynamics, Hydrodynamics, Optimization, or a related engineering discipline. A PhD is desirable but not mandatory.
Language: English (proficiency required for collaboration and documentation)
Instruction: English
- Proven experience applying machine learning and deep learning to engineering or physical systems.
- Strong proficiency in Python for scientific programming, with experience in C++, MATLAB, or similar languages.
- Familiarity with deep learning frameworks such as PyTorch, TensorFlow, or JAX.
- Experience with engineering simulation tools like STAR-CCM+ for CFD, hydrodynamics, or vessel performance.
- Understanding of naval architecture, ship hydrodynamics, or vessel performance analysis.
- No explicit nationality or residency restrictions mentioned.
- Open to candidates with relevant academic and professional experience.
Funding & terms
How to apply
Deadline: 2026-11-16 (Europe/London)
Applicants must submit their CV and cover letter through the University of Southampton’s job portal. A detailed job description and person specification are available for reference. Contact the recruitment team via email or phone for assistance.
- CV
- Cover letter
- Job Description and Person Specification (linked in the source)
Contact
Create a free profile to unlock your personal match score, the full requirements, funding details and how to apply — in English or Persian.