About Maxion Maxion Therapeutics is a biotechnology company developing antibody-based drugs for previously untreatable ion channel- and G protein-coupled receptor (GPCR)-driven diseases, including autoimmune conditions, chronic pain, and cardiovascular disease. The Company is developing a pipeline of potentially first- and best-in-class therapeutics using its proprietary KnotBody ® technology to generate potent, selective, and long-acting therapeutics by combining naturally occurring mini-proteins (‘knottins’) with antibodies using state-of-the-art phage and mammalian display technologies. Maxion was founded in 2020 by highly respected biotech entrepreneurs and scientists Dr John McCafferty ( CTO ) and Dr Aneesh Karatt- Vellatt ( CSO ). Dr McCafferty previously co-invented antibody phage display, which was the subject of the 2018 Nobel Prize in Chemistry awarded to his co-inventor Sir Gregory Winter. Maxion’s portfolio and growth is being advanced by a team of highly experienced leaders in the discovery and development of antibody-based drugs. The Company is based near Cambridge, UK and is backed by international blue-chip investors. For more information, please visit: https://www.maxiontherapeutics.com/. About the Role We are seeking a highly skilled Senior AI Research Scientist with expertise in computational protein design and generative protein modelling to enabling AI- and structure-guided approaches to therapeutic antibody and KnotBody ® design. The successful candidate will drive the development, implementation, deployment and adoption of generative AI/ML models to enable therapeutic protein design, engineering and optimisation, utilising Maxion’s proprietary KnotBody ® technology. This is a unique opportunity for someone who is excited to roll up their sleeves, build new capabilities from the ground up, and drive forward discovery programmes. The successful candidate will bring strong technical skills, a collaborative mindset, and the ability to thrive in a fast-paced biotech environment. Key Responsibilities Develop the computational protein design platform through integration, adaptation and benchmarking of generative protein design & engineering tools (AlphaFold/ OpenFold, RFDiffusion, ProteinMPNN, Boltz, FrameFlow, etc) into the drug discovery process. Build generative and predictive models for protein design by training and fine-tuning ML models (VAEs, diffusion models, transformers) focused on prediction of functional therapeutic proteins and their properties (affinity, stability, and developability). Enable computational optimisation of therapeutic proteins, leveraging various ML approaches (genetic algorithms, Bayesian optimisation, physics-based methods, etc.) and integrating experimental data. Build datasets, data pipelines, training workflows, and evaluation tools for model training, benchmarking, and continuous learning. Cross functional collaboration with internal R&D and discovery teams to translate predictive models into deployable tools and testable experimental hypotheses. Candidate Profile Ph.D. or MSc. in Computational Biology, Computer Science, Bioinformatics, Natural Sciences or a related subject. Essential skills/experience Strong programming skills in Python and experience with deep learning frameworks (e.g. PyTorch, JAX, TensorFlow in order of preference ). Substantial experience of structural bioinformatics and computational protein design, for example: protein structure modelling & prediction, generative protein sequence & structure design, protein-protein docking, physics-based modelling & simulation, etc Experience training and fine-tuning ML models for protein design or related tasks. Experience of integrating computational predictions with experimental validation data for property optimisation. Experience working with modern MLOps stacks (Docker, Kubernetes, CI/CD, GitHub, etc. ) to deploy and monitor models. Experience working with antibody sequence and structure datasets, using in silico tools for predicting protein properties and guiding engineering campaigns. Desirable skills/experience Publication(s) in relevant peer-reviewed journals, ideally focused on antibody design, AI/ML based protein modelling, or non-standard scaffolds (e.g. knottins, minibinders, etc.). Experience applying generative or structure-based models to challenging target classes (e.g. ion channels, GPCRs). What can we offer you? A competitive salary based on experience A comprehensive benefits package including generous pension contribution, Private Life and Medical Insurance, Cycle to Work Scheme, participation in the company Share Option Scheme, on site parking and more. Significant opportunities for career progression within a dynamic company. Located in a state-of-the art Science Park with easy access to Cambridge by car, train and bus, and offering on-site gym, cafe, and a vibrant social community. Working alongside an innovative team of scientists, including the founders, who are Key Opinion Leaders in the field. A supportive work environment with a key focus on fostering collaborative working environment within a friendly team. This is a permanent position. Closing date for applicatio ns: 12th January 2026 Agencies : We are recruiting this role with our selected recruitment partner - PIR International. If you need to get in touch regarding the role please reach out directly to the contact at PIR: nehal@pir-intl.com .