Postdoctoral Scientist – Multimodal Representation Learning for Predictive Biology

About the role

Johnson & Johnson Innovative Medicine is seeking a Postdoctoral Scientist to advance AI/ML analytics and multimodal modeling for drug discovery. The two‑year fixed‑term position will focus on deep learning for imaging microscopy and multi‑omics, integrating high‑content data to generate new biological insights.

Key responsibilities

• Design, develop, implement and validate AI/ML solutions using multimodal data of perturbed cells.
• Analyze large‑scale heterogeneous datasets (imaging microscopy, phenomics, transcriptomics, proteomics) to extract novel biological insights.
• Develop computer‑vision methods to quantify cellular heterogeneity.
• Collaborate with cross‑functional scientists and engineers to advance algorithms and product development.
• Communicate technical methodologies and present findings to diverse stakeholders.
• Maintain documentation and an up‑to‑date code repository.
• Draft manuscripts and disseminate research findings in peer‑reviewed venues.

Required profile

• Ph.D. in Electrical Engineering, Biomedical Engineering, Computer Science, Applied Mathematics, or related field (completed within 3 years or to be completed within 6 months).
• Strong expertise in AI/ML for biological applications with a proven publication record in top‑tier conferences or journals.
• Experience with foundation models or multimodal modeling of biological data (e.g., Cell Painting, imaging microscopy, multi‑omics).
• Excellent analytical and communication skills.

Required skills

• Python programming.
• Deep‑learning frameworks such as PyTorch or TensorFlow.
• Knowledge of Transformers, CNNs, graph networks, self‑supervised and multi‑instance learning.
• Computer‑vision techniques for cellular image analysis.
• Multimodal representation learning and data integration.