Machine Learning Scientist, Generative Modelling

The role

You will design and implement generative modelling approaches to learn intervention effects from biological data. You will develop models for generalization, counterfactual prediction, and experimental design while collaborating with experimental teams.

What you will do

• Design and implement generative modelling approaches that learn intervention effects from diverse biological data.
• Develop models focusing on generalisation, counterfactual prediction, and experimental design.
• Collaborate with experimental teams to design and validate computational hypotheses.
• Evaluate models for causal coherence, mechanistic fidelity, and utility in guiding real-world interventions.
• Communicate findings clearly to colleagues and stakeholders from different disciplines.

Required qualifications

• PhD in ML, statistics, computer science, or a related quantitative field.
• Deep expertise in generative modelling.
• Strong foundations in probabilistic modelling, representation learning, or neural network architectures for structured or sequential data.
• Excellence in Python.
• Familiarity with scalable ML tooling and high-performance computing.
• A disciplined approach to model evaluation with experience designing experiments to test real-world utility.
• Willingness and ability to engage deeply with biological data.

Nice to have

• Prior experience with single-cell or perturbational datasets
• Track record of impactful publications or open-source contributions in ML
• Experience working in interdisciplinary teams or applying ML in real-world settings

About the company

Relation is a TechBio company developing transformational medicines using single-cell multi-omics, functional assays, and machine learning. They operate with state-of-the-art wet and dry labs in London.