Senior Genomics ML Scientist: DNA Sequence Modelling

Relation Therapeutics; City Of London; On-site; GBP 70,000 - 120,000; Full time

Job summary

Relation Therapeutics is seeking a Senior Data Scientist to advance DNA sequence modelling, statistical machine learning, and functional genomics for target discovery. You will develop models linking genetic variation to phenotypes and disease biology, and work with the Rosalind team to link sequence to function, including variant effect prediction and regulatory activity modelling.

You will collaborate with interdisciplinary teams, validate hypotheses, and contribute to publications.

Qualifications

• PhD required in a quantitative field.
• Post-PhD experience, ideally in industry, biotech, or pharma.
• Experience with DNA language models, genomic foundation models, or transformer-based sequence models.
• Strong Python (preferred) and R skills; HPC experience advantageous.

Responsibilities

• Develop ML models for DNA sequence, regulatory elements, and genetic variation in disease contexts.
• Benchmark models for sequence-to-function tasks like variant effect and regulatory activity prediction.
• Integrate sequence-derived representations with transcriptomic and epigenomic datasets to uncover disease mechanisms.
• Collaborate with experimental and ML researchers to validate hypotheses and guide studies.
• Communicate results clearly to stakeholders and contribute to publications and project docs.
• Provide high-quality documentation and support scientific excellence and external visibility.

Skills

Python

R

Machine learning

Statistics

Education

PhD in computational biology, ML, statistics, genomics, bioinformatics or related

Tools

DNA language models

Genomic foundation models

Transformer-based sequence models

Job description

Relation Therapeutics is seeking a Senior Data Scientist to advance DNA sequence modelling, statistical machine learning, and functional genomics for target discovery. You will develop models linking genetic variation to phenotypes and disease biology, and work with the Rosalind team to link sequence to function, including variant effect prediction and regulatory activity modelling.

You will collaborate with interdisciplinary teams, validate hypotheses, and contribute to publications.