Job Description

The Role

Join AstraZeneca’s Oncology R&D in our Beijing R&D Center as a Machine Learning and AI Specialist and help shape the future of drug discovery. At AstraZeneca, we are building a variety of AI powered tools to accelerate the drug discovery process. In this role you will be responsible for implementing AI architectures for prediction of properties and 3D structures of small and large molecules complexes. Together with your colleagues you will create enhanced data sets for retraining and focusing these methods for specific use cases. You will benchmark different methods and build optimal pipelines for delivering accurate and impactful predictions. You will operate in a collaborative environment with other specialists in China and globally within R&D, and you’ll be encouraged to publish and present your work at leading conferences.

Expectations of a Successful Candidate

You will:

• Design, build and scale machine learning models (e.g., transformers, diffusion models, graph-based generative models) for molecular and biological property and structure prediction, leveraging large-scale molecular simulation, structural, assay and multi-omics data.
• Build scalable workflows Create and maintain distributed computing pipelines on cloud/cluster environments (e.g. PyTorch, TensorFlow, DeepSpeed, Horovod, MPI, Nvidia Apex/AMP) and work with containerisation (e.g., Docker, Kubernetes) and orchestration.
• Own protein co-folding and prediction workflows Lead the implementation, benchmarking and optimisation of protein-ligand and protein-protein complex prediction. Define metrics, analyse results and drive decisions on algorithmic direction.
• Champion innovation and best practice Evaluate emerging computational methodologies and AI technologies; relevant to the role. Benchmark and optimise these methods to define best practise.
• Communicate and influence Present complex results clearly to multidisciplinary audiences, guide experimental plans, and contribute to project strategy.
• Publish externally In high-quality journals and present at national and international conferences.

Required Skills and Qualifications

• Education PhD (or equivalent experience) in Computational Chemistry, Cheminformatics, Bioinformatics, Computer Science or a closely related discipline.
• Core expertise Strong track record with machine learning and AI methods. Experience of a range of machine/deep learning algorithms and architectures (e.g. graph neural networks, transformers).
• AI application Demonstrated interest and significant practical experience building and applying predictive or generative AI/ML methods in a chemistry or biophysics context.
• Programming and workflows Expert level proficiency with Python (and/or R, C++, Java), libraries for ML (e.g. scikit-learn, PyTorch, DeepChem, Tensorflow), modern optimisation techniques and experience with pipelining tools.
• Ways of working Excellent communication, presentation, teamwork, influencing, and time management skills.

Desirable Skills and Qualifications

• Computational chemistry methods breadth Knowledge and understanding of protein structure and dynamics modelling, and structure/ligand-based design.

• Medicinal chemistry fundamentals Good knowledge of physicochemical and ADME properties and their impact on molecule quality and progression.
• Experience working in a drug discovery environment (industry or academia) is an advantage

• Experience with multilabel and multitask machine-learning frameworks, especially for molecular/property prediction scenarios. For instance, recent work shows the value of modelling correlations among multiple labels (e.g., multi-property or multi-target settings) and leveraging hierarchical task-structures or prompt-based graph networks to improve multi-label prediction.
• Large scale computing experience with large-scale cloud computing, GPU acceleration and parallelisation
• Strong background in molecular/property modelling representation learning for molecules (graphs, SMILES, 3D geometry), generative models (VAEs, generative diffusion), self-supervised pre-training in chemical space.
• Hands-on experience with databases, data warehousing and retrieval systems (e.g., SQL, NoSQL, graph databases, data lakes, large-scale data integration from chemical, assay and literature sources).
• Proven knowledge of deep-learning frameworks beyond the basics: e.g., Hugging Face Transformers, DGL – deep graph libraries, PyG (PyTorch Geometric), JAX/Flax, DeepSpeed, Megatron-LM.
• Familiarity with workflow orchestration and MLOps tooling Airflow, Prefect, Dagster, Kubeflow, MLflow, DVC, clear understanding of CI/CD for ML, model monitoring, data drift detection.
• Publications Peer-reviewed publications in computational chemistry, cheminformatics, or AI for drug discovery.

About AstraZeneca

AstraZeneca is a global, science-led biopharmaceutical company committed to transforming patients’ lives through innovative medicines. In Oncology R&D, we combine deep biological insight with state-of-the-art AI to accelerate molecular design and decision-making. Our teams operate in an open, collaborative environment across Beijing (China), Cambridge (UK) and Boston (USA), sharing best practice and pushing the boundaries of computational chemistry and machine learning. By joining us as a Senior Scientist, you will contribute to a vibrant community of scientists pioneering computer-aided drug design – and have the platform to publish, present, and shape the next wave of innovation.

Date Posted

05-3月-2026

Closing Date

AstraZeneca embraces diversity and equality of opportunity. We are committed to building an inclusive and diverse team representing all backgrounds, with as wide a range of perspectives as possible, and harnessing industry-leading skills. We believe that the more inclusive we are, the better our work will be. We welcome and consider applications to join our team from all qualified candidates, regardless of their characteristics. We comply with all applicable laws and regulations on non-discrimination in employment (and recruitment), as well as work authorization and employment eligibility verification requirements.