Senior Scientist, AI for Discovery — New Target Discovery

b Overview /b p In this hands-on role, you will apply AI and biology to build and deploy agentic AI and predictive models that accelerate new drug target discovery across AstraZeneca’s therapeutic areas. You will translate scientific challenges into AI-enabled solutions and contribute to cross-functional target discovery workflows. You’ll write production-quality code and collaborate to share insights through publications and collaborations. This is a space to shape next-generation AI methods in drug discovery at a leading biopharma company. /p b Pay / Benefits /b ul li hybrid working model (minimum in-office days) /li li flexible working arrangements /li li opportunity to publish and present research /li li collaborative, interdisciplinary environment /li li advanced research infrastructure /li li global company with scientific impact /li /ul b Responsibilities /b ul li Understand therapeutic-area challenges with scientists to accelerate target identification and validation using agentic AI and predictive models. /li li Build and deploy multi-agent AI systems into therapeutic-area workflows to generate actionable scientific insights. /li li Develop, evaluate, and benchmark predictive foundation models for in silico biology (perturbation prediction, virtual cell models, preclinical efficacy forecasting). /li li Write production-quality code, pipelines, and tools for the team and broader organization. /li li Collaborate in cross-functional project teams and communicate technical findings to diverse audiences. /li li Contribute to AstraZeneca’s external visibility through publications, conferences, and collaborations. /li /ul b Key requirements /b ul li PhD in computational biology, bioinformatics, AI/ML, systems biology, or related quantitative discipline, or a Bachelor’s/Master’s with equivalent experience. /li li Experience with agentic AI, LLM-based reasoning systems, or multi-agent architectures in scientific problems. /li li Experience with predictive AI modeling for biology—foundation models, graph neural networks, perturbation models, or virtual cell approaches. /li li Understanding of drug discovery biology—target identification, validation, mechanism of action, translational science. /li li Strong Python proficiency; production-quality code, pipelines, and tools for scientific applications. /li li Hands-on experience with deep learning frameworks (PyTorch, JAX, or equivalent). /li li Effective communication of technical findings to diverse audiences. /li li Enthusiasm and persistence in applying AI methods to complex biological problems. /li /ul ul li Effective communication /li li Collaborative mindset /li li Persistence and curiosity /li li Python /li li PyTorch /li li JAX /li /ul