Join AstraZeneca's Oncology R&D at our Beijing R&D Center as a Machine Learning And Ai Specialist and help shape the future of multispecific antibody discovery and engineering. At AstraZeneca, we are building AI-enabled computational capabilities to accelerate the design and optimization of next-generation biologics. In this role, you will implement and apply methods for predicting the properties, structures and functions of antibodies and multispecific antibody formats, with a focus on sequence-to-structure-to-function modelling and developability. Together with colleagues, you will build enhanced datasets and optimize AI, structural-modelling and physics-based methods for virtual screening, antibody–antigen and protein–protein complex modelling, epitope and functional assessment, and early- and late-stage developability prediction and engineering. You will benchmark methods and build robust pipelines that support prospective experimental decisions. You will operate in a collaborative environment with specialists in China and globally across R&D, and you will be encouraged to publish and present your work at leading conferences.
Expectations of a Successful Candidate
You will design, build and apply computational models: Develop machine-learning, structural-biology and physics-based approaches for antibody and multispecific antibody property, function and structure prediction, using sequence, structural, affinity, functional and developability data. Build virtual screening and modelling workflows: Implement and optimize workflows for candidate prioritization, antibody–antigen and protein–protein complex prediction, epitope assessment, and multispecific antibody architecture and format evaluation. Enable developability prediction and engineering: Develop and apply methods to identify and mitigate developability risks in monoclonal and multispecific antibodies, including expression, assembly, stability, aggregation, solubility, viscosity, non-specific binding and manufacturability. Apply and benchmark innovative methods: Evaluate emerging AI, protein-design, structural-modelling and computational methods; adapt methods using internal and public data, including low-data approaches such as transfer learning and active learning; and define best practice for specific discovery applications. Build scalable workflows: Create and maintain reproducible data-processing, modelling and inference pipelines using Python-based ML tools and appropriate cloud, GPU or high-performance-computing environments. Communicate and influence: Present complex results clearly to multidisciplinary audiences, guide prospective experimental plans, contribute to project strategy, and publish in high-quality journals or present at national and international conferences.
Required Skills And Qualifications
Education: PhD, or equivalent experience, in Machine Learning, Computer Science, Computational Biology, Bioinformatics, Structural Biology, Biophysics, Protein Engineering, Computational Chemistry or a closely related discipline. Core expertise: Strong track record in one or more relevant areas, including machine learning, AI for biology, computational protein design, structural bioinformatics, molecular modelling, antibody engineering or biophysics. AI and computational application: Practical experience developing, applying or evaluating computational methods for protein, antibody, molecular or structural datasets, such as machine learning, protein sequence analysis, protein-structure prediction, protein–protein interaction modelling or molecular simulation. Programming and workflows: Strong proficiency in Python and relevant scientific-computing or ML libraries, such as PyTorch, JAX, TensorFlow, NumPy, SciPy, scikit-learn, DeepChem or equivalent tools; experience with modelling and pipelining workflows. Ways of working: Excellent communication, presentation, teamwork, influencing and time-management skills, with the ability to translate computational outputs into actionable experimental and project recommendations.
Desirable Skills And Qualifications
Multispecific antibody experience: Experience in multispecific antibody discovery or engineering, including relevant experimental work with antibody formats, protein engineering, binding or functional characterization, and/or biologics developability. Structure and developability modelling: Experience using protein-structure prediction, antibody–antigen or protein–protein complex modelling, molecular modelling or simulation, and/or prediction of biologics properties such as stability, aggregation, solubility, viscosity, expression or manufacturability. Large-scale computing and publications: Experience with GPU, cloud or high-performance computing, parallelisation or containerised workflows; peer-reviewed publications in machine learning, computational biology, structural biology, protein engineering or related fields.
Tagged as: Life Sciences
Development China Translational Medicine Scientist Development China Translational Medicine Scientist combines the understanding of disease biology with prior experience in...
ApplyMedia Development Scientist When you are part of the team at Thermo Fisher Scientific, you'll do important work. Surrounded by...
ApplyOncology Biostatistics Senior Associate Director Support the early Oncology clinical drug research and development process by providing strategic planning and...
ApplyOpen Rank Scientist We are seeking two In Vivo Pharmacologists to join our team of Target Progression at Novo Nordisk...
ApplyBoehringer Ingelheim Human Pharmaceutical Business With global presence, Boehringer Ingelheim has industry-leading expertise in medicine research and development. We are...
ApplyScientist I Join us as a Scientist I at Thermo Fisher Scientific, you'll discover meaningful work that makes a positive...
ApplyPlease visit astrazeneca.wd3.myworkdayjobs.com.
Don't forget to mention that you found the position on jobRxiv!
