Main Responsibilities:
1. Design, develop, and apply machine learning models to predict safety-relevant endpoints (e.g., liver or kidney toxicity) using chemical structure and biological data.
2. Integrate chemoinformatics and in vitro safety data, with the potential to expand toward transcriptomics or other omics technologies.
3. Provide in silico support for discovery and early development programs, offering scientific insights into potential safety risks.
4. Leverage internal data and external knowledge bases to enhance model performance and interpretability.
5. Collaborate closely with toxicologists, pharmacologists, data scientists, and chemists to co-create solutions and ensure models are meaningful and relevant.
6. Contribute to broader efforts such as biological read-across, reverse translation of historical data, and refinement of digital workflows for safety decision-making.
Qualifications and Experience:
7. Relevant working/residency permit or Swiss/EU-Citizenship required
8. PhD or MSc (with relevant experience) in Computational Toxicology, Cheminformatics, Bioinformatics, Data Science, Pharmacology, or a related field.
9. Solid experience in developing machine learning models, ideally applied to chemical and biological data.
10. Strong foundation in cheminformatics/chemistry, including working with molecular descriptors, chemical similarity, and structure-based analyses.
11. Experience with toxicological datasets and safety endpoints such as DILI or nephrotoxicity.
12. Familiarity with in vitro safety data and an interest in integrating complex biological datasets.
13. Proficient in programming (e.g., Python, R) and using scientific computing libraries (e.g., RDKit, scikit-learn, Pandas, TensorFlow, or similar).
14. Excellent communication and collaboration skills; able to translate technical insights for interdisciplinary teams.