Postdoctoral Research Scientist - AI for Bionanoscience

Postdoctoral Research Scientist - AI for Bionanoscience

Department of Physiology, Anatomy and Genetics, Kavli Institute for Nanoscience Discovery, Dorothy Crowfoot Hodgkin Building, South Parks Road, Oxford, OX1 3QU

Contract & job type: Full-time, Fixed-term for 18 months

About us:

The  Kavli Institute for Nanoscience Discovery Kavli Institute for Nanoscience Discovery (Kavli INsD), established in March 2021, brings together over 30 faculty and 450 researchers across disciplines to tackle global health challenges. By fostering interdisciplinary collaboration and providing cutting-edge facilities, it encourages innovation and shared discovery, and benefits from the close proximity of the scientific departments as well as advanced imaging and characterisation facilities and state-of-the-art-instrumentation.

At the   Department of Physiology Anatomy & Genetics (DPAG)  we undertake discovery science where we reassemble physiological processes at the molecular, cellular, tissue and systems level of organisation. In so doing we provide a bridge to translational medicine, and interface between physical and life sciences. We are committed not only to innovative research and the highest standard of teaching, but also to creating an inclusive and supportive working environment.

Overview of the role:

We are seeking to appoint two Postdoctoral Research Scientists in AI for Bionanoscience to join Professor Dame Molly Stevens’s lab at the Kavli Institute for Nanoscience Discovery, University of Oxford. We are seeking creative, motivated and collaborative researchers to develop next-generation AI methods for scientific and biomedical discovery.

The posts span two complementary research directions:

• AI for experimental science and multimodal scientific data analysis -- developing machine learning methods to support experimental design, interpretation and analysis of complex scientific datasets across biomaterials, biosensing, diagnostics and tissue engineering.
• AI for autonomous molecular and materials discovery -- developing predictive, generative and foundation- model-based AI methods for molecular optimisation, biomaterials engineering, protein and binder design, lipid nanoparticle formulation and materials discovery.

Successful candidates will contribute to one or both of these areas depending on expertise and interests.

The role is highly multidisciplinary and collaborative, involving close collaboration with experimental and computational researchers, with opportunities to develop AI systems capable of advancing scientific discovery in areas including advanced therapeutics and disease diagnostics. Postholders will work within a vibrant research environment comprising multiple interconnected projects in fundamental and applied bionanoscience, and will collaborate with internationally recognised academic and industrial partners.

The Stevens Group is internationally recognised for pioneering work in biomaterials research (  ) and operates at the interface of materials science, chemistry, biology, bioengineering and medicine, enabling highly collaborative and multidisciplinary research. The lab is strategically affiliated with the Department of Physiology, Anatomy and Genetics and the Institute of Biomedical Engineering within the Department of Engineering Science.

We welcome applicants from machine learning, AI, computer science, computational chemistry, physics, mathematics and related quantitative disciplines. Candidates with strong computational and methodological expertise who are excited to apply AI to challenging scientific problems are encouraged to apply, even if they have limited prior experience in biology, chemistry or materials science.

Key responsibilities:

• Develop, adapt and apply machine learning and AI methods to scientific problems in biomaterials, molecular and materials discovery and data-driven experimental science.
• Build robust and reproducible computational workflows for multimodal scientific data analysis, model development and validation.
• Work closely with experimental and computational researchers to define tractable machine learning problems, analyse complex multimodal scientific datasets, and translate model outputs into scientifically meaningful insights.
• Develop or adapt machine learning methods including supervised, self-supervised, generative and active learning approaches for scientific applications.

See Job Description for a full list of responsibilities.

Selection criteria:

• Hold, or be close to completing, a PhD/DPhil in either a computational discipline (e.g. machine learning, computer science, computational chemistry, applied mathematics, or data science), or a scientific discipline (e.g. biology, chemistry, materials science, biomedical science, or physics) with demonstrated expertise in computational research.
• Strong expertise in modern machine learning, statistical modelling, and scientific computing, including experience developing and evaluating computational models and reproducible workflows following appropriate data management practices.
• Strong programming skills, particularly in Python, and experience with relevant machine learning frameworks such as PyTorch, TensorFlow, JAX, or scikit-learn.
• Experience analysing complex scientific datasets in particular related to biomolecular design, materials discovery, chemical biology, formulation design, or related areas.

See Job Description for a full list of criteria.

What we offer:

• Your wellbeing at work matters, so we offer a range of family friendly and financial benefits including:
• An excellent contributory pension scheme
• 38 days annual leave
• A comprehensive range of childcare services
• Family leave schemes
• Cycle and electric car loan schemes
• Employee Assistance Programme
• Membership to a variety of social and sports clubs
• Discounted bus travel and Season Ticket travel loans

While this is a full-time role, we welcome applications from individuals who wish to be considered for part-time working or other flexible working arrangements.

How to apply:

Please submit:

• A CV including publications, relevant technical projects, and links to representative code repositories, preprints or other technical outputs (e.g. GitHub, GitLab or personal website), highlighting your contributions where appropriate.
• A 1-page statement describing your previous work, relevant experience, and future research interests in AI for scientific discovery and/or biomedical research.
• The contact details of two referees.

The closing date for applications is 12 noon on 01 July 2026.

Interviews are likely to take place during the week commencing 20 July 2026, and will be held on Microsoft Teams.

Applications are particularly welcome from women, black and minority ethnic candidates who are under-represented in academic posts in Oxford.

Follow us:

Stay connected with us on   ,   Bluesky and   to learn more about our work and culture. Informal enquiries about the role may be directed to the DPAG HR Team:   hr @dpag.ox.ac.uk

DPAG’s Statement of Inclusion:

We, as a Department and Community, will be considerate and welcoming of all people, regardless of age, disability, gender reassignment, marriage and civil partnership, pregnancy and maternity, race, religion or belief, sex, sexual orientation, gender identity, and socio-economic background. We acknowledge societal inequalities and how these impact us, and those around us, personally and professionally. Our policies, practices and   Respectful Behaviours Framework underpin this commitment.

DPAG and Sustainability:

We have signed up to The Laboratory Efficiency Assessment Framework (LEAF) and Green Impact, actively implementing and encouraging eco-friendly practices that reduce waste, promote energy efficiency, and promote bio-diversity. See the job description for more detail.

Contact Person : Vacancy ID : 186868

Contact Phone : Closing Date & Time : 01-Jul-2026 12:00

Pay Scale : RESEARCH GRADE 7 Contact Email :

Salary (£) : 39424 - 47779

Click on the link(s) below to view documents

Filesize

186868 PDRS AI Bionanoscience JD 543