ABOUT MULTUS

Our mission is to transform human and planetary health by designing cell culture media to fuel the industrial bioeconomy.

We serve companies in the cellular agriculture, advanced therapies and the biopharmaceutical sectors, developing and supplying cell culture media to accelerate their transition from lab to market.

If you are passionate about driving the growth of a sustainable bioeconomy we encourage you to apply and play your part in creating a better future for people and the planet!

ABOUT THE ROLE

This internship offers the opportunity to contribute to a high-impact R&D project at the intersection of machine learning, software engineering, and biotechnology. The work supports the development of computational tools that enhance how we collect, process, and learn from experimental data — helping to improve data quality, consistency, and the speed of our optimisation workflows.

Interns will explore and develop methods that combine software engineering with machine learning to build robust, reusable analytical pipelines. The project involves working with rich experimental datasets and developing approaches to extract reliable, quantitative insights from complex biological data.

This is a genuine blend of software engineering (building well-architected, maintainable systems) and data science/ML (training and evaluating models), making it ideal for candidates who enjoy working across both disciplines.

The role is ideal for students with a strong interest in applied machine learning, software engineering, or data science — particularly in scientific or industrial research contexts.

The internship is a paid fixed-term full-time contract for a minimum of three months, with a flexible start date in summer 2026. We welcome applications from students and recent graduates from any university.

RESPONSIBILITIES

• Exploring and evaluating a range of machine learning and analytical approaches to extract quantitative insights from complex biological data
• Building reproducible computational pipelines for training, evaluating, and deploying ML models
• Working with deep learning architectures and exploring the use of transfer learning to adapt models across different experimental contexts
• Developing tooling and infrastructure to support standardised, repeatable analytical workflows
• Working with large-scale experimental datasets
• Collaborating with cross-functional teams to integrate computational outputs into experimental workflows