Senior Scientist, AI for Discovery — Safety and New Target Discovery

Hace 2 días

España AstraZeneca Jornada completa
Role Based in Barcelona
- 3 days onsite/ 2 days at home About AstraZeneca At AstraZeneca, we put patients first and strive to meet their unmet needs worldwide. Working here means being entrepreneurial, thinking big and working together to make the impossible a reality. If you are swift to action, confident to lead, willing to collaborate, and curious about what science can do, then you're our kind of person. We are a global, science-driven biopharmaceutical company dedicated to discovering, developing, and delivering innovative medicines that enrich the lives of patients. Our R&D engine combines deep biology expertise with cutting-edge artificial intelligence to accelerate how we find and validate new drug targets — ultimately bringing life-changing therapies to patients faster. About Our Site AstraZeneca’s Barcelona hub brings together a dynamic, growing team at the forefront of data science, R&D, and technology. Over the past two years the site has grown rapidly, and we are continuing to expand. Barcelona’s vibrant life-sciences community and its position as one of Europe’s most dynamic cities make it an ideal location for talent from around the world —

we offer
relocation packages to ensure geography doesn’t stand in the way. Here you will work in an inclusive, collaborative environment with a commitment to lifelong learning, growth, and development. About the Team The AI for Discovery team builds and deploys AI capabilities — including agentic AI, predictive foundation models, and multimodal representation models — to accelerate target discovery, drug design, and safety assessment across AstraZeneca R&D. We are now establishing dedicated AI support for safety science, working alongside Clinical Pharmacology and Safety Sciences (CPSS) to build predictive models that help scientists assess and anticipate safety risks earlier in the drug discovery process. This is a new capability — you will help build it from the ground up. The team partners closely with safety scientists, toxicologists, and translational teams, as well as AI engineering and AI research groups across the organisation. What the Role Involves This is a hands-on individual contributor role applying AI to safety science and new target discovery. You will apply your technical skills in AI and biology to build, evaluate, and deploy predictive models and agentic AI tools that support safety assessment and risk prediction across AstraZeneca’s portfolio.

Key responsibilities
· Build, evaluate, and deploy predictive AI models that integrate multimodal data — including omics (transcriptomics, Cell Painting), chemical structure, and in vitro assay data — to predict safety outcomes.
· Develop and benchmark multimodal foundation models and representation learning approaches, combining diverse biological and chemical data sources into unified embeddings for downstream safety prediction.
· Build confidence and uncertainty quantification methods — calibration, conformal prediction, out-of-distribution detection — to help scientists judge when model outputs can reliably inform safety decisions.
· Contribute to the development of agentic AI tools and automated pipelines that support safety scientists in querying, integrating, and interpreting heterogeneous evidence.
· Write production-quality code, maintain reproducible experimental pipelines, and contribute to shared infrastructure alongside AI engineers.
· Collaborate effectively with safety scientists, toxicologists, and computational biologists — communicating technical findings to both expert and non-expert audiences.
· Contribute to AstraZeneca’s external visibility through publications, conference presentations, and scientific collaborations. Essential Skills
· Degree in computational biology, bioinformatics, AI/ML, systems biology, cheminformatics, or a related quantitative discipline, with relevant research or industry experience. Candidates with additional post-doctoral experience are equally encouraged to apply.
· Experience with predictive AI modeling for biology or chemistry — foundation models, graph neural networks, multimodal representation learning, or related approaches.
· Understanding of drug discovery or safety science — including toxicology, mechanism of action, safety pharmacology, or translational science.
· Strong technical proficiency in Python (required); experience building production-quality code, pipelines, and tools for scientific applications.
· Hands-on experience with deep learning frameworks (PyTorch, JAX, or equivalent) for model development and evaluation.
· Experience working with large-scale biological or chemical datasets (e.g., transcriptomics, Cell Painting, high-content imaging, in vitro screening data).
· Effective communication of technical and scientific findings to diverse audiences.
· Enthusiasm and persistence in applying AI methods to complex biological and safety problems. Desirable Skills
· PhD in a relevant discipline.
· Experience with uncertainty quant