(Senior) Postdoctoral Research Scientist - Biological Foundation Models
- The Earlham Institute
- Norwich, Norfolk
- Aug 31, 2026
Full time
Engineering
Job Description
(Senior) Postdoctoral Research Scientist - Biological Foundation Models
Job Title (Senior) Postdoctoral Research Scientist - Biological Foundation Models Post Number Closing Date 20 Aug 2026 Grade SC6/SC5 Starting Salary Salary: £39,000-£52,560
Hours per week 37 Project Title Generative Digital Biology: Multimodal Foundation Models for Cross-Scale Modeling Expected/Ideal Start Date 07 Sep 2026 Months Duration 36
Job Description Main Purpose of the Job The post holder will conduct primary research in the AI for Biology Group to develop large-scale multimodal foundation models. Potentially ranging from hundreds of millions to tens of billions of parameters where scientifically justified, to underpin the Generative Digital Biology programme. The role will focus on original AI methods for pretraining, post-training, adaptation and evaluation across biological modalities, including DNA and RNA sequences, genomics, transcriptomics, single-cell and spatial omics, imaging, phenotypic and perturbation data. The successful candidate will join at a rare moment: early enough to help shape a new programme at EI, but with strong technical foundations, prior publications, existing collaborations and a clear research trajectory already in place. The aim is not simply to apply existing machine learning tools to biological datasets, but to build new AI systems that can represent biological mechanisms across scales and enable experimentally grounded discovery. The ambition is to move beyond static biological representation learning towards predictive, transferable and experimentally grounded models of living systems. The post holder will help build the representation and prediction layer of the Generative Digital Biology programme: models that can connect molecular, regulatory, cellular, tissue and organismal scales, support biological hypothesis generation, and enable downstream experimental design. This will be a highly collaborative role embedded across EI. The post holder will work with EI colleagues and platforms to develop AI-ready biological data resources and benchmarks, including
Main Activities & Responsibilities Percentage Develop original multimodal foundation model architectures for biological data, including sequence, genomics, transcriptomics, single-cell and spatial omics, imaging, phenotype and perturbation modalities.
For appointment at SC5, take intellectual and operational leadership of a defined foundation-model workstream, set scientific priorities and milestones, manage technical risks, and deliver the work with limited supervision (essential for SC5) 25 Design and implement large-scale pretraining, post-training, fine-tuning, adaptation and evaluation pipelines for biological AI models using GPU, HPC and/or cloud computing and reproducible research workflows. 20 Work with EI colleagues, including BioFAIR, ELIXIR-UK, Open and FAIR Data and Research e-Infrastructure teams, to help define AI-ready biological data atlases, metadata standards, model and dataset documentation, and foundation-model-ready benchmarks. 15 Build transferable representations that connect molecular, regulatory, cellular, tissue and organismal scales, and evaluate their utility for prediction, perturbation response and biological discovery. 15 Collaborate with Cellular Genomics, Single-cell and Spatial Analysis, Earlham Biofoundry, engineering biology and other EI groups to identify biological use cases and translate model outputs into experimentally useful hypotheses or designs.
For appointment at SC5, coordinate the relevant interdisciplinary collaboration and ensure that model outputs are translated into a coherent programme of experimentally actionable hypotheses or designs (essential for SC5). 10 Develop benchmark tasks, ablation studies, uncertainty estimates and robustness/generalization analyses to assess biological validity, transferability and downstream utility. 5 Prepare manuscripts and conference papers for leading AI, machine learning, computational biology and life science venues; present findings internally, nationally and internationally.
For appointment at SC5, lead the preparation and submission of major research outputs and represent the work in relevant external forums (essential for SC5) 5 Contribute to research proposals, grant applications, open-source software, model cards, dataset documentation and good research practice, including responsible data handling and reproducibility.
For appointment at SC5, make substantive contributions to grant development and provide scientific or technical guidance to junior researchers or students (essential for SC5). 5 As agreed with line manager, any other duties commensurate with the nature of the role.
Person Profile Education & Qualifications Requirement Importance PhD (awarded or expected within 6 months) in Computer Science, Machine Learning, Artificial Intelligence, Computational Biology, Mathematics, Statistics, Physics, Engineering or a related quantitative discipline Essential
Specialist Knowledge & Skills Requirement Importance Excellent programming skills in Python and practical experience with PyTorch, JAX, TensorFlow or equivalent deep learning frameworks, ideally including large-scale model training ecosystems such as Hugging Face, DeepSpeed, FSDP, Megatron-LM, Ray or equivalent tools Essential Experience with large-scale model training, GPU/HPC/cloud computing, Linux, version control and reproducible research workflows Essential Understanding of biological data types such as DNA/RNA sequences, genomics, transcriptomics, single-cell, spatial, imaging, phenotypic or perturbation datasets Desirable Experience with FAIR data, metadata standards, biological data atlases, benchmark datasets, model cards, dataset documentation or reusable ML resources Desirable Demonstrable experience developing or leading foundation-model research in biology or another complex scientific domain (essential for SC5) Desirable A strong track record of independent or semi-independent research in machine learning, AI, computational biology, bioinformatics or a closely related field (essential for SC5) Desirable Ability to develop and deliver a research direction with limited supervision, including project planning, collaboration and communication with interdisciplinary partners (essential for SC5) Desirable
Requirement Importance Evidence of high-quality outputs appropriate to career stage in AI/ML, computational biology, bioinformatics or AI for science, demonstrated through peer-reviewed publications and/or significant open-source models, datasets or benchmark contributions Essential Experience designing, adapting or evaluating original AI algorithms rather than only applying existing tools Essential Experience working with large biological datasets, multi-omics data, single-cell/spatial data or cross-modal biological prediction tasks Desirable Experience contributing to externally funded research projects, open-source software, benchmark datasets, data/model resources or collaborative research consortia Desirable Clear evidence of leading high-quality research outputs, for example first-author publications, substantial contributions to major papers in top AI conferences (essential for SC5) Desirable Ability to support junior group members, contribute to collaborative projects, and help develop future publications and grant applications (essential for SC5) Desirable
Interpersonal & Communication Skills Requirement Importance Ability to work independently, use initiative, solve complex research problems and deliver against agreed milestones Essential Excellent written and verbal communication skills . click apply for full job details
Job Title (Senior) Postdoctoral Research Scientist - Biological Foundation Models Post Number Closing Date 20 Aug 2026 Grade SC6/SC5 Starting Salary Salary: £39,000-£52,560
Hours per week 37 Project Title Generative Digital Biology: Multimodal Foundation Models for Cross-Scale Modeling Expected/Ideal Start Date 07 Sep 2026 Months Duration 36
Job Description Main Purpose of the Job The post holder will conduct primary research in the AI for Biology Group to develop large-scale multimodal foundation models. Potentially ranging from hundreds of millions to tens of billions of parameters where scientifically justified, to underpin the Generative Digital Biology programme. The role will focus on original AI methods for pretraining, post-training, adaptation and evaluation across biological modalities, including DNA and RNA sequences, genomics, transcriptomics, single-cell and spatial omics, imaging, phenotypic and perturbation data. The successful candidate will join at a rare moment: early enough to help shape a new programme at EI, but with strong technical foundations, prior publications, existing collaborations and a clear research trajectory already in place. The aim is not simply to apply existing machine learning tools to biological datasets, but to build new AI systems that can represent biological mechanisms across scales and enable experimentally grounded discovery. The ambition is to move beyond static biological representation learning towards predictive, transferable and experimentally grounded models of living systems. The post holder will help build the representation and prediction layer of the Generative Digital Biology programme: models that can connect molecular, regulatory, cellular, tissue and organismal scales, support biological hypothesis generation, and enable downstream experimental design. This will be a highly collaborative role embedded across EI. The post holder will work with EI colleagues and platforms to develop AI-ready biological data resources and benchmarks, including
- with BioFAIR and ELIXIR-UK on FAIR, interoperable and foundation-model-ready data;
- with the Cellular Genomics programme and Single-cell and Spatial Analysis platform on single-cell and spatial omics;
- and with the Earlham Biofoundry and engineering biology colleagues on model-guided experimental design.
Main Activities & Responsibilities Percentage Develop original multimodal foundation model architectures for biological data, including sequence, genomics, transcriptomics, single-cell and spatial omics, imaging, phenotype and perturbation modalities.
For appointment at SC5, take intellectual and operational leadership of a defined foundation-model workstream, set scientific priorities and milestones, manage technical risks, and deliver the work with limited supervision (essential for SC5) 25 Design and implement large-scale pretraining, post-training, fine-tuning, adaptation and evaluation pipelines for biological AI models using GPU, HPC and/or cloud computing and reproducible research workflows. 20 Work with EI colleagues, including BioFAIR, ELIXIR-UK, Open and FAIR Data and Research e-Infrastructure teams, to help define AI-ready biological data atlases, metadata standards, model and dataset documentation, and foundation-model-ready benchmarks. 15 Build transferable representations that connect molecular, regulatory, cellular, tissue and organismal scales, and evaluate their utility for prediction, perturbation response and biological discovery. 15 Collaborate with Cellular Genomics, Single-cell and Spatial Analysis, Earlham Biofoundry, engineering biology and other EI groups to identify biological use cases and translate model outputs into experimentally useful hypotheses or designs.
For appointment at SC5, coordinate the relevant interdisciplinary collaboration and ensure that model outputs are translated into a coherent programme of experimentally actionable hypotheses or designs (essential for SC5). 10 Develop benchmark tasks, ablation studies, uncertainty estimates and robustness/generalization analyses to assess biological validity, transferability and downstream utility. 5 Prepare manuscripts and conference papers for leading AI, machine learning, computational biology and life science venues; present findings internally, nationally and internationally.
For appointment at SC5, lead the preparation and submission of major research outputs and represent the work in relevant external forums (essential for SC5) 5 Contribute to research proposals, grant applications, open-source software, model cards, dataset documentation and good research practice, including responsible data handling and reproducibility.
For appointment at SC5, make substantive contributions to grant development and provide scientific or technical guidance to junior researchers or students (essential for SC5). 5 As agreed with line manager, any other duties commensurate with the nature of the role.
Person Profile Education & Qualifications Requirement Importance PhD (awarded or expected within 6 months) in Computer Science, Machine Learning, Artificial Intelligence, Computational Biology, Mathematics, Statistics, Physics, Engineering or a related quantitative discipline Essential
Specialist Knowledge & Skills Requirement Importance Excellent programming skills in Python and practical experience with PyTorch, JAX, TensorFlow or equivalent deep learning frameworks, ideally including large-scale model training ecosystems such as Hugging Face, DeepSpeed, FSDP, Megatron-LM, Ray or equivalent tools Essential Experience with large-scale model training, GPU/HPC/cloud computing, Linux, version control and reproducible research workflows Essential Understanding of biological data types such as DNA/RNA sequences, genomics, transcriptomics, single-cell, spatial, imaging, phenotypic or perturbation datasets Desirable Experience with FAIR data, metadata standards, biological data atlases, benchmark datasets, model cards, dataset documentation or reusable ML resources Desirable Demonstrable experience developing or leading foundation-model research in biology or another complex scientific domain (essential for SC5) Desirable A strong track record of independent or semi-independent research in machine learning, AI, computational biology, bioinformatics or a closely related field (essential for SC5) Desirable Ability to develop and deliver a research direction with limited supervision, including project planning, collaboration and communication with interdisciplinary partners (essential for SC5) Desirable
Requirement Importance Evidence of high-quality outputs appropriate to career stage in AI/ML, computational biology, bioinformatics or AI for science, demonstrated through peer-reviewed publications and/or significant open-source models, datasets or benchmark contributions Essential Experience designing, adapting or evaluating original AI algorithms rather than only applying existing tools Essential Experience working with large biological datasets, multi-omics data, single-cell/spatial data or cross-modal biological prediction tasks Desirable Experience contributing to externally funded research projects, open-source software, benchmark datasets, data/model resources or collaborative research consortia Desirable Clear evidence of leading high-quality research outputs, for example first-author publications, substantial contributions to major papers in top AI conferences (essential for SC5) Desirable Ability to support junior group members, contribute to collaborative projects, and help develop future publications and grant applications (essential for SC5) Desirable
Interpersonal & Communication Skills Requirement Importance Ability to work independently, use initiative, solve complex research problems and deliver against agreed milestones Essential Excellent written and verbal communication skills . click apply for full job details
About The Earlham Institute