Principal Staff Scientist in Essex

Do you want to help us improve human health and understand life on Earth? Make your mark by shaping the future to enable or deliver life-changing science to solve some of humanity’s greatest challenges. We are looking for a Principal Staff Scientist (computational) to provide analytical leadership in Artificial Intelligence/ Machine Learning (AI/ML) and genomic data analysis across the Human Genetics Programme.

About the Programme: The Human Genetics Programme brings together large-scale human cohorts, deep molecular profiling and linked patient records to build robust, clinically useful models of human disease. Our goal is to generate the datasets and models that explain who develops disease, when and why, and to turn that understanding into better prediction, prevention and treatment across diverse populations. We are building clinic-anchored cohorts that are explicitly designed for prediction and causal inference. Working with healthcare partners, we recruit patients in real-world clinical settings, collect repeat samples from relevant tissues, and link these to rich outcomes data. Across these cohorts we generate multiomic data at scale, using broadly deployable assays such as serum proteomics, metabolomics and transcriptomics, alongside whole-genome sequencing.

Faculty groups in the Programme work together on shared, centrally generated cohorts and datasets. These datasets have a common structure: repeat molecular measurements linked to clinical outcomes over time. That means groups face the same analytical challenges, including learning from sparse, high-dimensional and time-resolved data, separating causal drivers from downstream correlates, and building models that hold up in new populations and healthcare settings. AI and ML methods are well placed to address these challenges. The Programme already has considerable analytical and statistical strength across its groups, including colleagues extending their work into AI/ML. We are now looking for a Principal Staff Scientist to lead and coordinate that effort, and to set the direction for how AI/ML develops across the Programme.

What you'll be doing: You will provide strategic direction and oversight for AI/ML across the Programme, working with the statisticians, computational scientists and analysts already in our faculty groups, and contributing hands-on to the analysis yourself. This spans predictive modelling and causal inference, and the full range of our data, from genetic and functional genomic data through to longitudinal multiomic and clinical data from patients. You will shape the Programme's analytical strategy and lead on how models are built and validated for clinical use. A central part of the role is analytical consistency: methods, tools and standards developed for one project should be available to the rest, so that expertise built in one group benefits everyone.

Most of your hands-on work will be on projects in the Anderson group, which studies inflammatory bowel disease. Open IBD is an inception cohort of 2,000 patients, recruited prior to diagnosis and sampled repeatedly from that point, generating scRNA-seq of gut biopsies, whole-genome sequencing and stool microbiome data alongside linked clinical records. This gives molecular profiles from before diagnosis and treatment, and disease trajectories that can be modelled from onset. IBD-Response is a multi-centre study of treatment response in IBD, combining scRNA-seq of PBMCs, serum proteomics and stool microbiome sequencing with genetic data to predict which patients will benefit from which therapy.

This is a senior appointment. You will be the lead intellectual driver for the Programme's AI/ML strategy, sit on the Programme Working Group, contribute to strategic decisions, and represent the Programme in this area within Sanger and externally.

What the role gives you: An opportunity to shape how the Programme uses AI and ML to deliver its mission to build predictive models with real clinical impact: who develops disease, how it progresses, and who will respond to which treatment. You will help set the Programme's research direction as a member of the Programme Working Group, and be a visible leader within the Programme and beyond. You will have access to human cohort data at a scale few places can offer, spanning genetic, multiomic and linked clinical data, alongside world-leading high-throughput scientific pipelines through our Scientific Operations teams, substantial compute, and established clinical partnerships. The Programme holds extensive research funding that can be deployed to support projects, which allows large-scale work to be launched quickly. The Programme is at an early stage, so there is real scope to shape how we build models, what standards we work to, and how our analytical infrastructure develops.

About you: You will have a PhD and an established independent research record in statistical genetics, computational biology, statistics, machine learning, epidemiology or a related quantitative discipline, with substantial expertise in AI/ML methods for building disease predictors from high-dimensional biological and clinical data, and significant experience of analysing human genetic and genomic data at scale. You will have validated predictive models in independent cohorts and populations, and understand what it takes to move a model into clinical or health system use. You will still write code and work with data yourself. You will enjoy setting direction for a community of quantitative scientists, helping colleagues extend their work into AI/ML, and working alongside people on their own projects. We would also welcome experience with IBD or other immune-mediated inflammatory disease, longitudinal cohort design, treatment response prediction, or work in industry or a healthcare setting.

Essential Skills:

• PhD in statistical genetics, computational biology, statistics, mathematics, machine learning, epidemiology or a related quantitative discipline
• Extensive experience in an applied research or technical development environment, with a significant track record of delivering complex research projects, evidenced by publications and other outputs
• Recognised as an expert in the broader scientific community in AI/ML or statistical methods for human genetics and disease prediction, with evidence of methods, tools or analytical approaches being taken up by others or translated into real world benefit
• Substantial expertise in AI/ML methods for building disease predictors from high-dimensional biological and clinical data
• Experience with human genetic and genomic data at scale, for example GWAS, sequencing, or molecular data such as scRNA-seq, proteomics or metabolomics
• Extensive working knowledge of applied research methods, including statistical analysis, study design and good research practice
• Experience validating predictive models in independent cohorts and populations, and an understanding of what it takes to move a model into clinical or health system use
• Demonstrable recent experience of personally writing code and analysing data at scale, with good software practice including version control, reproducible workflows, testing and documentation
• Experience managing, supervising or mentoring scientific staff, and of initiating and driving external collaborations, including with clinical or industry partners
• Excellent communicator, able to build relationships and inspire confidence and respect at all levels, including with clinical and non-specialist audiences
• Sound judgement about model limitations, bias and performance across populations
• Demonstrates inclusivity and respect for all

Other Information: For further details please see role profile. For informal queries, please contact Carl Anderson at ca3@sanger.ac.uk.

Salary per annum (dependent upon skills and experience): 65-85k

Contract type: Permanent

Hybrid role, minimum of 3 days per week on Campus.

Application Process: Please apply with your CV and a cover letter outlining how you meet the criteria set out above and in the role profile. Interviews will take place week commencing 2nd November 2026. Closing Date: 15th October 2026.

Hybrid Working at Wellcome Sanger: We recognise that there are many benefits to Hybrid Working; including an improved work-life balance, with more focused time, as well as the ability to organise working time so that collaborative opportunities and team discussions are facilitated on campus. The hybrid working arrangement will vary for different roles and teams. The nature of your role and the type of work you do will determine if a hybrid working arrangement is possible.

Equality, Diversity and Inclusion: We aim to attract, recruit, retain and develop talent from the widest possible talent pool, thereby gaining insight and access to different markets to generate a greater impact on the world. We have a supportive culture with the following staff networks: LGBTQ+, Parents and Carers, Disability, Gender Equity and Race Equity to bring people together to share experiences, offer specific support and development opportunities and raise awareness. The networks are also a place for allies to provide support to others. We believe people do their best work when they can be their authentic selves. That’s why we’re committed to creating a truly inclusive culture at Sanger Institute. We will consider all individuals without discrimination and are committed to creating an inclusive environment for all employees, where everyone can thrive.

Our Benefits: We are proud to deliver an awarding campus-wide employee wellbeing strategy and programme. The importance of good health and adopting a healthier lifestyle and the commitment to reduce work-related stress is strongly acknowledged and recognised at Sanger Institute. Sanger Institute became a signatory of the International Technician Commitment initiative In March 2018. The Technician Commitment aims to empower and ensure visibility, recognition, career development and sustainability for technicians working in higher education and research, across all disciplines.

Summary Location: Hinxton, Cambridgeshire Type: Full time