About the Opportunity:
As a Thesis Worker at AstraZeneca, you’ll find an environment that’s full of unique opportunities and exciting challenges. Here, you’ll have the opportunity to pursue your areas of interest whilst equally developing a broad skillset and knowledge base to get the best out of your experience. You’ll be working on meaningful projects to make an impact and deliver real value for our patients and our business.
Thesis Work Description:
The MolecularAI group at AstraZeneca uses start-of-the-art artificial intelligence (AI), machine learning algorithms, molecular simulation, and data science to develop models and tools that are used daily in drug discovery projects. We have developed several open-source platforms such as ReInvent for molecular design, AiZynthFinder for synthesis planning, and Maize for advanced simulation pipelines. We are now looking for students who will further develop our models and address their current limitations. Some projects will involve collaboration with experimental and computational chemistry departments of AstraZeneca. There are several projects that can be tailored to the student’s interest, including:
• Evaluation of agentic AI architectures
• AI methods in synthesis and reactivity prediction, covering ML, chemoinformatics, quantum chemistry in combination
• AI methods in analytical chemistry science for reaction data analysis and structure elucidation
• Flow matching models for molecules and conformers
• Exploring novel deep learning architectures
• Uncertainty and multi-objective optimization in reinceforcement learning
• Combining machine learning with simulations in macro-molecular drug design
• Ligand binding affinity prediction with machine-learned potentials
• Investigating the effect of model bias in molecular property prediction
• Molecular property prediction in low-data regime
• Context-aware molecular property prediction
• Multi-domain/multi-modal learning for molecular foundation models