Data Scientist (1-year fixed-term contract)

About the Role

Portal Biotech is hiring a Data Scientist to join its Bioinformatics & Machine Learning team for a fixed term of one year. In this position, you will work closely with the wet lab to apply statistical and machine learning methods to create new uses for Portal’s single-molecule proteomics platform. The role covers everything from early-stage exploratory analysis to building reliable production-ready methods, all within a fast-paced and highly collaborative research setting at the cutting edge of the field.

The ideal person for this role enjoys tackling new methodological problems, works with scientific discipline and first-principles thinking, and feels comfortable operating in spaces that change quickly and are often not fully defined.

Key Responsibilities

• Build, refine, and deliver analytical workflows for nanopore-based proteomic datasets.
• Develop and apply statistical and machine learning methods for new biological data, progressing from initial exploratory work to deployable pipeline elements.
• Assess and compare algorithmic approaches thoroughly, and document the outcomes clearly.
• Work closely with experimental scientists and engineers to interpret data behaviour, understand requirements, and stay aligned on outputs.
• Explain analytical findings and methodological choices to mixed audiences, including people without technical backgrounds and external clients.
• Help strengthen the team’s standards around scientific discipline, reproducibility, and code quality across the wider organisation.

Requirements

• Master’s degree or above in Bioinformatics, Statistics, Machine Learning, or a closely related discipline.
• Strong theoretical understanding of statistics and machine learning, with the ability to use that knowledge in biological settings.
• Good command of data science and machine learning best practices, including major Python libraries, experimentation workflows, Git, and the ability to understand and adapt existing code.
• Practical data engineering capability, including working with messy datasets, applying careful cleaning and validation, and making sound decisions as complexity grows.
• A thoughtful perspective on how AI tools should and should not be used in everyday technical work.
• Ability to move code from notebook-based analysis into reusable and dependable pipeline components.
• Familiarity with experiment tracking tools and shared compute environments and/or cloud platforms.
• Strong scientific curiosity and a “data hunter” mindset, with comfort asking clarifying questions and handling ambiguous or underspecified problems.
• Ability to collaborate across experimental, engineering, and commercial teams, and to explain complex technical ideas to non-specialists.
• Collaborative approach with an outward-looking mindset and the ability to communicate technical value in terms of customer and business outcomes.

Desirable Experience

• Background in molecular biology or protein biochemistry, with a foundational understanding of proteomics concepts.
• Experience creating data science pipelines for omics or other complex biological datasets, including familiarity with relevant standards and file formats.
• Exposure to unsupervised or semi-supervised learning, Bayesian modelling, or time-series analysis.
• Interest in or experience with single-molecule or electrophysiology data.
• Ability to learn new biological domains, data types, or analytical techniques quickly.

Additional Information

This is a one-year fixed-term contract based onsite in London, England, United Kingdom. The company offers a competitive salary and benefits package. Candidates must have full, unrestricted, and immediate right to work in the UK.

If you are excited about building advanced scientific tools and contributing to major innovations in proteomics, this opportunity may be a strong fit.

Terms & Conditions

This role is offered as a fixed-term position for 12 months.

Only candidates with immediate and unrestricted UK work authorisation can be considered.