Principal Data Scientist

Barrington James; England; Hybrid; GBP 150,000 - 200,000; Full time

Job summary

A biotechnology recruitment firm is looking for a Principal Data Scientist to integrate internal and external datasets for drug discovery. The role involves developing predictive models and collaborating with scientific teams. Ideal candidates should have a PhD or MSc in relevant fields and experience with biomedical datasets. Strong skills in Python or R and machine learning frameworks like TensorFlow or PyTorch are required. This is a hybrid position based in London.

Qualifications

• Strong experience applying machine learning to biomedical datasets.
• Demonstrated ability to work with large-scale public datasets.
• Hands-on expertise building data pipelines and predictive models.

Responsibilities

• Assess the feasibility of machine learning approaches.
• Integrate external resources with in-house datasets.
• Build and evaluate machine learning pipelines for drug sensitivity.
• Partner with biology teams for computational solutions.

Skills

Machine learning application

Data curation and integration

Model development

Collaboration with teams

Strong communication skills

Education

PhD or MSc in Computational Biology, Bioinformatics, or related field

Tools

Python

R

scikit-learn

TensorFlow

PyTorch

Job description

Principal Data Scientist

Location : London (Hybrid)

Sector : AI-Driven Drug Discovery / Oncology Biotech

About the Company

I am recruiting on behalf of an early‑stage biotechnology company developing next‑generation antibody‑based therapeutics for oncology. Their platform combines synthetic biology, high‑throughput phenotypic screening, and data‑driven discovery to identify differentiated drug candidates with improved precision and therapeutic index. As our screening capabilities scale, we are generating large, multimodal datasets across cytotoxicity, target expression, and molecular features. We are now seeking a Principal Data Scientist to transform these datasets into actionable insights that guide drug discovery and candidate prioritization.

Role Overview

The Principal Data Scientist will shape and execute the strategy for integrating internal screening outputs with external biological datasets to drive predictive modelling, target evaluation, and drug candidate selection. This is a hands‑on scientific and technical role : in addition to providing strategic guidance, you will prototype analytical pipelines, curate and integrate complex datasets, and build predictive models that form the foundation of our long‑term AI and data initiatives.

Key Responsibilities

1. Strategy & Advisory

• Assess the feasibility and optimal application of machine learning approaches to high‑throughput phenotypic datasets.
• Recommend suitable modelling frameworks for drug‑target sensitivity prediction and screening data interpretation.
• Advise on data infrastructure, computational workflows, and architecture needed to support scalable AI adoption.

2. Data Curation & Integration

• Identify, evaluate, and curate relevant external datasets, including:
  • Cancer cell line resources
  • Patient‑derived datasets
  • Target expression databases
  • Protein and compound knowledgebases
• Integrate external resources with in‑house phenotypic and molecular datasets to create unified, analysis‑ready data assets.
• Ensure data quality, interoperability, and biological relevance for downstream predictive modelling.

3. Model Development & Prototyping

• Build and evaluate machine learning pipelines to model relationships between cytotoxicity, target expression, molecular features, and payload sensitivity.
• Explore AI‑driven approaches for drug repurposing and candidate prioritisation.
• Benchmark modelling strategies, quantify performance trade‑offs, and communicate results clearly to technical and non‑technical stakeholders.

4. Collaboration & Knowledge Transfer

• Partner closely with biology and screening teams to translate experimental questions into computational solutions.
• Contribute to long‑term planning for data science hiring, infrastructure, and tooling.
• Produce clear documentation, methodological recommendations, and prototype pipelines ready for internal scaling.

Desired Qualifications

• PhD or MSc in Computational Biology, Bioinformatics, Computer Science, Statistics, or a related quantitative field.
• Strong experience applying machine learning to biomedical datasets, especially in areas such as drug repurposing, pharmacogenomics, or precision oncology.
• Demonstrated ability to work with large‑scale public datasets (e.g., DepMap, CCLE, LINCS, GDSC, TCGA, UniProt).
• Hands‑on expertise building data pipelines and predictive models using Python and/or R, including ML frameworks such as scikit‑learn, TensorFlow, or PyTorch.
• Familiarity with high‑throughput screening datasets, cytotoxicity assays, or drug sensitivity profiling is a strong plus.
• Ability to balance strategic thinking with practical execution in a fast‑moving biotech environment.
• Strong communication skills and proven ability to collaborate with cross‑functional scientific teams.

If this role sounds of interest, I'd love to talk with you!

Following your application, Jay Robins, a specialist AI recruiter will discuss the opportunity with you in detail.

He will be more than happy to answer any questions relating to the industry and the potential for your career growth.

The conversation can also progress further to discussing other opportunities, which are also available right now or will be imminently becoming available.

This position has been highly popular, and it is likely that it will close prematurely. We recommend applying as soon as possible to avoid disappointment.