Snr Data Scientist, Computational Genomics/DNA Modelling

The opportunity

This is a unique opportunity for a senior data scientist to work on DNA sequence modelling, statistical machine learning, and functional genomics in support of target discovery and mechanism elucidation. You will develop and apply computational models that connect genetic variation and regulatory DNA sequence to downstream molecular phenotypes, cellular programmes, and disease biology. Embedded within the Rosalind team you will build and evaluate models that link sequence to function - including variant effect prediction,regulatory activity modelling and representation learning for genomic data.

Day to Day you will

• Develop and implement machine learning models for DNA sequence, regulatory elements, and genetic variation in disease-relevant contexts.

• Build, evaluate and benchmark models for sequence-to-function tasks such as variant effect prediction, regulatory activity prediction, and the interpretation of non-coding disease signals.

• Integrate sequence-derived representations with transcriptomic, epigenomic, and perturbational datasets to uncover disease mechanisms and support target prioritisation.

• Partner closely with experimental and machine learning researchers to validate hypotheses, interpret results, and guide downstream studies.

• Communicate findings clearly to internal stakeholders, including presenting methods, results, and recommendations.

• Contribute to publications, scientific communications, and project documentation, supporting scientific excellence and external visibility.

Professionally, you will have

• PhD in computational biology, machine learning, statistics, genomics, bioinformatics, or a related quantitative discipline.

• Post-PhD experience, ideally including time in an industry, biotech, or pharmaceutical environment.

• Experience with DNA language models, genomic foundation models, or transformer-based sequence models.

• Understanding of statistical machine learning and probabilistic modelling, with experience selecting and evaluating appropriate modelling approaches for complex biological datasets.

• Knowledge of statistical genetics methods (e.g fine-mapping, colocalisation,, or variant to gene approaches).

• High proficiency in Python (preferred) and R, with experience working in high-performance computing environments.

• Ability to operate independently, driving projects from concept through delivery.

Bonus experience

• Familiarity with single-cell transcriptomics or patient-derived datasets.

• Experience working in interdisciplinary teams within biotech or pharma settings.

• Experience integrating machine learning models with genomics, single-cell, or perturbation datasets.

• Familiarity with 3D genome / chromatin interaction data where relevant (Hi-C, Capture-C, etc.).