Bioinformatics Scientist – Role focus: Virtual Cells

Location: Central London, UK

We are working with a well-funded, highly innovative AI-driven biotechnology organisation operating at the intersection of computational science and human biology. The team generates its own proprietary data, develops general-purpose biological foundation models, and translates scientific discovery into meaningful research and clinical outcomes. The organisation’s first mission is to tackle the brain - to achieve a deep mechanistic understanding, protect it from neurological disease, and enhance it in health. Its growing, interdisciplinary team of AI researchers, experimental scientists, clinicians, and operators is distributed across London, San Francisco, and Dubai.

The team are now looking for a bioinformatics scientist to formulate and interrogate biologically meaningful hypotheses for neurological disease marker and target discovery through a virtual cell model.

The Role

• Design and structure experimental hypotheses grounded in available datasets and biological models, with clearly defined downstream evaluation criteria to assess performance.
• Identify, curate, and manage public and proprietary datasets spanning diverse multi-omic and multi-modal data types.
• Perform data quality control (QC) and exploratory and statistical analyses to ensure robustness and interpretability.
• Develop and maintain multi-omic bioinformatics pipelines to support integrative analysis.
• Engineer features and prepare datasets for downstream machine-learning workflows, as well as foundational AI model training and application.
• Collaborate closely with experimental and machine-learning teams to validate, interpret, and refine computational findings.
• Establish and manage external research collaborations with academic and industry partners focused on Alzheimer’s disease (AD) biology.

Experience Required

• A strong record of top-tier publications and demonstrated experience in patent development.
• Hands-on experience deriving biological insight from complex, multi-omic data in the context of virtual cell models, including genomics, epigenetics, transcriptomics, proteomics, and ATAC-seq.
• Production-grade software engineering skills, with the ability to write robust, maintainable code that forms the backbone of a scalable software stack.
• End-to-end experience with multi-omic data processing pipelines, from raw data ingestion through to downstream analytical outputs, including strong working knowledge of workflow managers such as Nextflow.
• Expertise in statistical methods for the analysis and evaluation of biological datasets.
• Strong working knowledge of cloud computing environments, including (but not limited to) AWS.
• Domain expertise in advanced artificial intelligence and machine-learning approaches, with practical experience applying them to biological problems.
• Proficiency in data wrangling, analysis, and visualization using Python (preferred), as well as R or Julia.
• Solid data engineering experience, including familiarity with large-scale data processing technologies such as Spark, Hadoop, and NoSQL databases.

Why Consider This Opportunity?

This position offers the chance to work within a mission-driven organisation at the forefront of AI-enabled biology, contributing directly to research with the potential to reshape disease understanding and therapeutic discovery. The environment is intellectually rigorous, fast-paced, and designed for individuals who want to have a tangible scientific impact. The company offers a competitive salary, potential equity package and other company benefits.