AI Scientist – AI-Driven Target Identification

Overview

In this role you will apply advanced AI/ML to extract insights from pre-clinical, clinical, and real-world data to advance target and biomarker discovery in oncology. You will work within the Oncology Data Science and AI & Innovation teams to leverage foundational, multimodal, and generative models, collaborating with cross-functional partners. Your work will shape drug discovery, biomarker strategies, and biomolecular modeling, contributing to publications and scientific communications. This position offers onsite work in Cambridge or Basel with relocation support and a focus on impactful, data-driven cancer research.

Pay / Benefits

• insurance plans
• retirement plans
• wellbeing resources
• global recognition programs
• flexible and hybrid working options
• minimum 14 weeks paid parental leave

Responsibilities

• Design, develop, and apply advanced AI/ML methods to multi-source datasets (pre-clinical, clinical, real-world)
• Demonstrate value of AI techniques for target ID, biomarker discovery, and drug development
• Leverage foundational models and multimodal/generative AI for drug discovery applications
• Collaborate with cross-functional teams to establish ML-ready data practices
• Contribute to scientific publications and present results at conferences

Key requirements

• PhD in Machine Learning, Computer Science, Applied Mathematics, Computational Biology or related field
• Strong experience in generative AI, biomedical foundation models, geometric deep learning, multimodal learning, or large-scale knowledge graphs
• Proficiency in PyTorch and deep learning frameworks; ability to learn new tools
• Experience across ML and LLM stack: feature engineering, model development, deployment, validation
• Prior work with omics data and familiarity with oncology drug development
• Excellent communication to convey complex insights to cross-functional teams
• Strong research track record with publications in top ML/AI venues or journals

• Excellent communication
• Cross-functional collaboration
• Curiosity and learning agility
• PyTorch
• Generative AI
• Biomedical foundation models

…