Postdoc, Autonomous Discovery & the AI Life Science Platform

About the role

P&G Singapore is recruiting a 2-year fixed-term Postdoc to join the Skin Bioscience Discovery Accelerator (SBDA) at its Innovation Center. The role helps define AI-enabled scientific discovery by combining multimodal biological data, predictive models, Design-Build-Test-Learn (DBTL) architectures and advanced life science platforms. You will work with P&G Research Fellows, senior technical leaders and international experts, and help build the digital-first discovery engine that connects AI with experimental biology.

Key responsibilities

• Pioneer new scientific frameworks and discovery approaches to advance understanding of biological performance, resilience, regeneration and health across the lifespan.
• Design and run high-impact research programs using advanced biology, human-relevant experimental systems, multimodal data and AI-enabled discovery.
• Work with P&G Research Fellows and global scientific leaders to shape scientific strategy and accelerate breakthrough discovery.
• Operate within a DBTL discovery environment, integrating experiments, computational approaches and emerging technologies.
• Turn discoveries into publications, intellectual property, external collaborations and technology opportunities.

Required profile

• PhD in AI, machine learning, computational biology, bioinformatics, computer science, computational life sciences, data science or a related field.
• Strong research record: publications, preprints, patents, open-source contributions, scientific software or platform development.
• Experience with complex biological or biomedical data streams or human-relevant model systems.
• Preferred: experience building AI-enabled discovery platforms, DBTL systems, multimodal foundation models, large language models for research, or active learning and causal inference methods.

Required skills

• AI for Science, machine learning for life sciences, multimodal data integration and predictive modeling of biological systems.
• DBTL architectures and closed-loop experimental learning systems.
• Programming, analytical and quantitative skills, able to turn scientific questions into computational architectures.
• Excellent written and verbal communication, and the ability to work independently and lead technically in cross-functional teams.