Z
Senior ML Scientist — Biomarker Discovery
Zara Patel
Full-time · Senior · London
About the role
Our drug discovery platform uses machine learning to identify and validate biomarkers for patient stratification in oncology clinical trials. The problem we are working on is specific: given high-dimensional genomic, transcriptomic, and imaging data from a Phase II trial cohort, identify the molecular signatures that predict treatment response with sufficient statistical confidence and biological plausibility to support a Phase III protocol amendment. We are not building a general-purpose tool. We are solving a specific bottleneck in the clinical trial process — the failure to identify the right patient population early enough — and we are building it in partnership with three pharmaceutical companies who are running active trials on our platform. The role requires a scientist who understands the biology well enough to evaluate whether a statistical finding makes mechanistic sense, and an engineer who understands the regulatory environment well enough to know what "validation" means when the output feeds into an FDA submission package. This is serious, careful work. The timeline is trials, not sprints.
Responsibilities
- Design and implement biomarker discovery analyses on Phase II trial datasets in collaboration with clinical and bioinformatics teams
- Develop and validate predictive models for treatment response, with documentation suitable for regulatory submission review
- Contribute to the statistical analysis plan for biomarker objectives in new trial protocols
- Present findings to pharmaceutical company partners — you will present to both technical and non-technical scientific audiences
- Maintain analytical reproducibility standards: version control, environment management, and analysis documentation
Requirements
- 6+ years of ML research or engineering with at least three years in a clinical, genomics, or biomedical context
- Python for data analysis, model development, and reproducible research workflows — Pandas, NumPy, and scientific Python ecosystem
- R for statistical analysis, Bioconductor workflows, and compatibility with biostatistics team outputs
- Statistics at clinical depth: survival analysis, multiple testing correction, mixed effects models, and the discipline to distinguish statistical significance from clinical relevance
- Scikit-learn and PyTorch for classification, clustering, and representation learning on high-dimensional biological data
- Familiarity with FDA guidance on AI/ML in drug development (2021 action plan and subsequent guidance) is a material advantage
- Experience with genomic data formats and analysis pipelines (TCGA, GEO, or similar) is a strong plus
Benefits
- Work directly on patient stratification problems in active oncology trials
- Hybrid — two days in our Cambridge, UK office, three days remote
- £85,000 – £105,000 base salary + annual bonus
- £2,500 annual conference and publication budget
- Access to real clinical trial datasets — not synthetic benchmarks
Job Type
Full-time
Level
Senior
Language
English
Salary Range
£85,000 – £105,000
AI Expertise
data science & analytics
Ready to apply for this role?
Create a free talent account in under 2 minutes.
- Apply to verified AI companies
- Get AI-matched job recommendations
- Message hiring managers directly
- Build your public AI talent profile