Data Scientist (1-year fixed-term contract)
Apply statistics and machine learning on raw signals acquired from Portal's protein sequencing platform to identify and characterise proteins, working collaboratively with the wet lab
We usually respond within a week
About the role
Portal is seeking a motivated Data Scientist to join our Bioinformatics & Machine Learning team. In this 1-year, fixed-term role, you will work directly with the wet lab, applying techniques from statistics and machine learning to invent new applications of Portal's single-molecule proteomics platform. The work spans the full range from exploratory data analyses to shipping production-hardened methods, and is embedded in a fast-moving, highly collaborative research environment at the scientific frontier of the field. This role is ideal for someone who is excited by novel methodological challenges, applies scientific rigour and first principles approach to their work, and is comfortable in rapidly evolving and often ambiguous problem spaces.
Tasks and responsibilities
Research, development, and shipping of analytical pipelines for nanopore-based proteomic data
Design and implementation of statistical and ML approaches to novel biological data, iterating from exploratory analysis through to deployable pipeline components
Robust evaluation and benchmarking of algorithmic approaches, with clear documentation of findings
Liaise with experimental scientists and engineers to understand data characteristics, interpret results, and align on deliverables
Present analytical results and methodological decisions to multidisciplinary audiences, including non-technical stakeholders and clients
Contribute to a culture of scientific rigour, reproducibility, and code quality within the team and outwards to the entire company
Experience & requirements
Qualifications
Master's degree or higher in Bioinformatics, Statistics, Machine Learning, or a related field
Technical
Strong theoretical grounding in statistics and ML, with the ability to apply it in biological contexts
Solid command of DS best practices: major Python DS/ML libraries, data science experimentation workflows, Git version control, and ability to read and reuse code from existing projects
Demonstrated data engineering fundamentals, including handling messy data, applying robust cleaning and validation practices, and exercising good judgement as data complexity increases
A genuine, considered view on the use of AI tools in day-to-day technical work, where they add value, and where they don't
Ability to ship code from analysis notebooks to robust, reusable pipeline components
Familiarity with experiment tracking tools and shared compute environments and/or cloud platforms
Behavioural
Demonstrates strong scientific curiosity and a data hunter mindset; asks good clarifying questions and is comfortable navigating complex, ambiguous, and under-specified problems
Ability to work effectively across experimental, engineering, and commercial functions, and explain complex technical work to non-specialist audiences
Strong internal and external collaborator, with an outward looking, market-aware mindset and the ability to articulate technical value in terms of customer and business impact
Desirable
A theoretical background in molecular biology or protein biochemistry, including foundational understanding of proteomics-related concepts
Hands-on experience developing data science pipelines for omics or other complex biological data, including familiarity with relevant data standards and formats
Experience with unsupervised or semi-supervised learning, Bayesian modelling, or time-series data
Experience with or interest in single-molecule or electrophysiology data
Demonstrated ability to learn new biological domains, data modalities, or analytical techniques quickly and effectively
We offer a competitive salary and benefits package. If you are passionate about developing cutting-edge scientific tools and want to contribute to breakthrough innovations in proteomics, we encourage you to apply!
This is a 1-year fixed-term position. This role requires candidates to have full, unrestricted, and immediate right to work in the UK.
- Team
- Bioinformatics (BiX)
- Role
- Data Scientist
- Locations
- London
About Portal Biotech
Founded by DNA-sequencing veterans, Portal Biotech is developing the first bench-top single-molecule protein sequencer, leveraging machine-learning algorithms and building on decades of in-house expertise in nanopore technology. By analysing full-length protein molecules at the single-molecule level, our platform delivers rapid, real-time information on protein identity, abundance, and structure. Those insights open frontiers in drug discovery, diagnostics, and fundamental research, helping scientists and clinicians to better understand human health and disease.