Machine Learning Scientist – Sequence Modelling

Job description

ABOUT RELATION Relation is an end-to-end biotech company developing transformational medicines, with technology at our core. Our ambition is to understand human biology in unprecedented ways, discovering therapies to treat some of life’s most devastating diseases. We leverage single-cell multi-omics directly from patient tissue, functional assays, and machine learning to drive disease understanding—from cause to cure. This year, we embarked on an exciting dual collaboration with GSK to tackle fibrosis and osteoarthritis, while also advancing our own internal osteoporosis program. By combining our cutting-edge ML capabilities with GSK’s deep expertise in drug discovery, this partnership underscores our commitment to pioneering science and delivering impactful therapies to patients. We are rapidly scaling our technology and discovery teams, offering a unique opportunity to join one of the most innovative TechBio companies. Be part of our dynamic, interdisciplinary teams, collaborating closely to redefine the boundaries of possibility in drug discovery. Our state-of-the-art wet and dry laboratories, located in the heart of London, provide an exceptional environment to foster interdisciplinarity and turn groundbreaking ideas into impactful therapies for patients. We are committed to building diverse and inclusive teams. Relation is an equal opportunities employer and does not discriminate on the grounds of gender, sexual orientation, marital or civil partnership status, gender reassignment, race, colour, nationality, ethnic or national origin, religion or belief, disability, or age. We cultivate innovation through collaboration, empowering every team member to do their best work and reach their highest potential. By joining Relation, you will become part of an exceptionally talented team with extraordinary leverage to advance the field of drug discovery. Your work will shape our culture, strategic direction and, most importantly, impact patients’ lives. THE OPPORTUNITY As a Machine Learning Scientist within the Rosalind team, you will design and apply advanced machine learning techniques to DNA and genetic data. This role is ideal for someone with a strong machine learning background and an interest in genetics. Your work will directly contribute to uncovering non-trivial associations between genetic variants and diseases, ultimately advancing therapeutic discovery. THE TEAM YOU WILL JOIN The Rosalind team aims to extract useful insights through representations of DNA, whether related to variants, genes or the regulatory mechanisms in between. Sitting at the forefront of ML for genomics, the team develops models that help uncover meaningful biological signals from DNA and turn them into foundations for our target discovery pipelines. The team also has a strong track record of publishing at major ML venues, including winning a Best Paper award for PatchDNA at the NeurIPS AI4D3 workshop and publishing recently in the main conference track at ICLR: https://iclr.cc/virtual/2026/poster/10011056. It’s an exciting opportunity to contribute to cutting-edge research, advance representation learning for DNA, and help build state-of-the-art models for understanding biology and disease. YOUR RESPONSIBILITIES - Develop and apply sequence modelling machine learning techniques to DNA sequences - Train, fine-tune and evaluate DNA sequence models for tasks including variant interpretation, gene discovery and regulatory modelling - Collaborate with computational and experimental scientists to generate and validate ML-driven hypotheses - Leverage large-scale external and internal datasets to build and adapt models for disease-focused applications - Design robust evaluations to measure model quality, biological relevance and translational value - Contribute to scientific innovation by applying the latest advances in machine learning and genomics. PROFESSIONALLY, YOU HAVE - A PhD in machine learning, computational biology, or a related field, or equivalent industrial experience - Demonstrated experience applying machine learning techniques to biological sequences or text - Proficiency in Python and at least one ML platform (e.g. PyTorch, TensorFlow) - Flexibility and the ability to tackle new challenges at the intersection of biology and machine learning. DESIRABLE KNOWLEDGE OR EXPERIENCE - Experience applying machine learning to biological sequences, including DNA or proteins - Strong understanding of transformers and their applications in biomedical research - Knowledge of lab-in-the-loop frameworks and integration of ML techniques with experimental data. PERSONALLY, YOU ARE - An inclusive leader and team player - A clear communicator - Driven by impact - Humble and eager to learn - Motivated and curious - Passionate about making a difference in patients’ lives Join us in this exciting role where your contributions will have a direct impact on advancing our understanding of genetics and disease risk, supporting our mission to bring transformative medicines to patients. Together, we’re not just doing research; we’re setting new standards in the field of machine learning and genetics. The patient is waiting! Relation is a committed equal opportunities employer. RECRUITMENT AGENCIES Please note that Relation does not accept unsolicited CVs from agencies. CVs should not be forwarded to our job aliases or employees. Relation Therapeutics will not be liable for any fees associated with unsolicited CVs.