Senior Machine Learning Scientist – AI Computational Biology (Remote, UK)
Location: Remote (UK-based, London time zone)
Type: Full-time
Focus: Genomics, single-cell biology, production ML systems ( RNA-Seq AND WGS)
The Opportunity
We’re building production-grade computational methods that turn complex biological data into robust, interpretable biomarkers used daily to advance cancer research and drug development.
This is not a purely exploratory research role. You’ll take true end-to-end ownership of methods that sit between raw omics data and biological interpretation — designing them, stress-testing them, and running them reliably in production.
If you enjoy combining deep machine learning, real biological signal, and strong engineering practices, this role is built for you.
What You’ll Do
Own production biomarker methods
- Design and implement genomics and transcriptomics pipelines (RNA-seq, single-cell, WGS/WES).
- Turn complex molecular data into scalable, reproducible biomarkers with clear assumptions and limitations.
- Continuously improve methods based on biological insight, feedback, and observed failure modes.
Apply ML & AI to biological interpretation
- Develop and fine-tune deep learning models for biological representation learning (e.g. Single-cell, multimodal data).
- Prototype AI-driven approaches (including LLMs and agentic workflows) for hypothesis generation and interpretation.
- Decide where ML meaningfully adds value — and where simpler methods are better.
Evaluate emerging methods
- Track new approaches from literature and open source.
- Implement, benchmark, and critically assess robustness and generalisability.
- Drive adoption decisions based on evidence, not novelty.
What We’re Looking For
Background
- MSc / PhD (or equivalent industry experience) in Machine Learning, Computer Science, Computational Biology, Bioinformatics, or related field.
- Strong interest in biology and translational research; oncology exposure is a plus.
Technical profile
- Strong Python skills with experience building complex ML or data-processing pipelines.
- Hands-on experience with omics data (single-cell RNA-seq, bulk RNA-seq, WGS/WES, or multimodal genomics).
- Deep learning experience (e.g. Transformers, VAEs, contrastive learning, GNNs).
- Familiarity with production-quality practices:
- Version control (Git)
- Reproducibility & testing
- Containerisation (Docker) and/or CI/CD
Mindset
- Enjoys owning methods long-term, not just publishing or prototyping.
- Comfortable working across biology, ML, and engineering.
- Able to clearly explain trade-offs to both technical and non-technical stakeholders.