Principal/Senior Data Scientist

Wellcome Sanger Institute
Saffron Walden
1 month ago
Applications closed

Related Jobs

View all jobs

Senior Data Scientist, AI-Driven Assessments Lead

Principal Data Scientist London, United Kingdom

Principal Data Scientist

Senior Data Scientist

Senior Data Scientist

Senior Data Scientist (Senior Software Engineer), BBC Verify

Principal Data Scientist

Salary Per Annum: £53,717 – £63,815


About the Role

You will lead and contribute to transformative projects that integrate single-cell genomics, spatial transcriptomics, and generative AI to build next-generation models for understanding tissue biology and cellular dynamics across organs such as the pancreas, kidney, skin, and liver.


Research Focus Areas

  • Spatial & Multi-omics Atlas Construction: Build large-scale spatial and single-cell atlases across diseased tissues (pancreas, kidney, skin, liver) using spatial transcriptomics, scRNA-seq, and multiome data in collaboration with leading Sanger groups.
  • Generative AI for Cell Fate & Perturbations: Develop diffusion, flow-matching, and transformer-based generative models to predict cell fate, tissue remodelling, and drug or perturbation responses in silico.
  • Foundational Models for Single-Cell Biology: Train large, generalizable deep models across public and internal datasets to support the Human Cell Atlas and broad Sanger research programs.
  • Open Targets Translational AI Projects: Apply foundational and multi-omics models to real-world challenges in drug discovery, target identification, and target safety in collaboration with major pharma partners.
  • Agentic AI for Scientific Reasoning & Experiment Design: Develop AI agents capable of hypothesis generation, experiment planning, and multi-step scientific workflows using reinforcement learning and tool-use models.
  • Core Machine Learning Research: Advance fundamental ML methods—including advanced generative modelling, scalable training algorithms, representation learning, and uncertainty modelling—tailored for biological data.
  • Multimodal Learning (Imaging + Genomics + Clinical Data): Create models that integrate histopathology imaging, spatial proteomics, single-cell genomics, and patient-level clinical data to learn unified biological and clinical representations.
  • Leap Project: Develop large-scale AI models to stratify patients using diverse multi-omics data, with a strong commitment to equity and inclusion, particularly in women’s health, in collaboration with Roser Vento-Tormo at the Sanger Institute.

About Us

Join the Lotfollahi Group, an interdisciplinary team of ML researchers, computational biologists, clinicians and experimentalists working with the Human Cell Atlas and international leaders.


Key Publications & References

  • Akbar Nejat et al., Mapping and reprogramming human tissue microenvironments with MintFlow (bioRxiv, 2025)
  • Birk et al., Quantitative characterization of cell niches in spatially resolved omics data, Nature Genetics (2025)
  • Jeong et al., SIGMMA: Hierarchical Graph-Based Multi-Scale Multi-modal Contrastive Alignment of Histopathology Image and Spatial Transcriptome (arXiv, 2025)
  • Sanian et al., 3D-Guided Scalable Flow Matching for Generating Volumetric Tissue Spatial Transcriptomics from Serial Histology (arXiv, 2025)

About You

We welcome applications from diverse backgrounds passionate about biology, foundation model development, modelling cellular perturbation responses, predicting patient behaviours and analysing multi-modal biological data.


Essential Skills

  • MSc and/or Ph.D. in a relevant quantitative discipline (e.g., Computer Science, Computational Biology, Genetics, Bioinformatics, Physics, Engineering, or Applied Statistics/Mathematics).
  • Proven experience using advanced statistical techniques, machine learning, and modern deep learning techniques.
  • Previous ML work experience in a scientific/academic environment (RA/Internships are considered as work experience).
  • Strong knowledge of Python, including core data science libraries such as Scikit-Learn, SciPy, TensorFlow, and PyTorch.
  • Knowledge of software development best practices and collaboration tools, including git-based version control, python package management, and code reviews.
  • Excellent communication skills, with the ability to explain complex machine learning algorithms and statistical methods to non-technical stakeholders.
  • Experience working with cloud environments and tools, such as Amazon AWS S3, EC2, etc.
  • Evidence of related work experience as a researcher in the area of Machine learning.
  • Strong publication record.
  • Ability to quickly understand scientific, technical, and process challenges and breakdown complex problems into actionable steps.
  • Ability to work in a frequently changing environment with the capability to interpret management information to amend plans.
  • Ability to prioritize, manage workload, and deliver agreed activities consistently on time.
  • Demonstrate good networking, influencing and relationship building skills.
  • Strategic thinking is the ability to see the ‘bigger picture.
  • Ability to build collaborative working relationships with internal and external stakeholders at all levels.
  • Demonstrates inclusivity and respect for all.

Additional Essential Skills for Principal Data Scientist

  • Experience in supervision (PhD students and Postdoctoral Fellows).
  • Experience in writing manuscripts for publication.
  • Experience working with cloud environments and tools, such as Amazon AWS S3, EC2, etc.
  • Relevant solid publication record in either machine learning or application of machine learning in biology.

Application Process

Please submit your CV and a cover letter detailing your research experience, interest in the focus area(s), and future aspirations. Closing Date: 8th February 2026.


Hybrid Working

We recognize hybrid working benefits, including an improved work-life balance and 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 staff networks, LGBTQ+, Parents and Carers, Disability and Race Equity to bring people together to share experiences, offer specific support and development opportunities and raise awareness. 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. 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.


#J-18808-Ljbffr

Subscribe to Future Tech Insights for the latest jobs & insights, direct to your inbox.

By subscribing, you agree to our privacy policy and terms of service.

Industry Insights

Discover insightful articles, industry insights, expert tips, and curated resources.

How Many Data Science Tools Do You Need to Know to Get a Data Science Job?

If you’re trying to break into data science — or progress your career — it can feel like you are drowning in names: Python, R, TensorFlow, PyTorch, SQL, Spark, AWS, Scikit-learn, Jupyter, Tableau, Power BI…the list just keeps going. With every job advert listing a different combination of tools, many applicants fall into a trap: they try to learn everything. The result? Long tool lists that sound impressive — but little depth to back them up. Here’s the straight-talk version most hiring managers won’t explicitly tell you: 👉 You don’t need to know every data science tool to get hired. 👉 You need to know the right ones — deeply — and know how to use them to solve real problems. Tools matter, but only in service of outcomes. So how many data science tools do you actually need to know to get a job? For most job seekers, the answer is not “27” — it’s more like 8–12, thoughtfully chosen and well understood. This guide explains what employers really value, which tools are core, which are role-specific, and how to focus your toolbox so your CV and interviews shine.

What Hiring Managers Look for First in Data Science Job Applications (UK Guide)

If you’re applying for data science roles in the UK, it’s crucial to understand what hiring managers focus on before they dive into your full CV. In competitive markets, recruiters and hiring managers often make their first decisions in the first 10–20 seconds of scanning an application — and in data science, there are specific signals they look for first. Data science isn’t just about coding or statistics — it’s about producing insights, shipping models, collaborating with teams, and solving real business problems. This guide helps you understand exactly what hiring managers look for first in data science applications — and how to structure your CV, portfolio and cover letter so you leap to the top of the shortlist.

The Skills Gap in Data Science Jobs: What Universities Aren’t Teaching

Data science has become one of the most visible and sought-after careers in the UK technology market. From financial services and retail to healthcare, media, government and sport, organisations increasingly rely on data scientists to extract insight, guide decisions and build predictive models. Universities have responded quickly. Degrees in data science, analytics and artificial intelligence have expanded rapidly, and many computer science courses now include data-focused pathways. And yet, despite the volume of graduates entering the market, employers across the UK consistently report the same problem: Many data science candidates are not job-ready. Vacancies remain open. Hiring processes drag on. Candidates with impressive academic backgrounds fail interviews or struggle once hired. The issue is not intelligence or effort. It is a persistent skills gap between university education and real-world data science roles. This article explores that gap in depth: what universities teach well, what they often miss, why the gap exists, what employers actually want, and how jobseekers can bridge the divide to build successful careers in data science.