Computational Toxicologist (m/f/d)

Workload: 100%, Hybrid possible
Start Date: As soon as possible (latest: 01.09.2025)

Key Responsibilities:

• Design and implement machine learning models to predict toxicity endpoints (e.g., DILI, nephrotoxicity) using chemical and biological datasets.

• Integrate cheminformatics with in vitro assay data, and potentially omics technologies, to enhance safety predictions.

• Deliver in silico safety support to discovery programs by interpreting model outputs and contributing scientific insights.

• Reuse and mine historical and external data to optimize model performance and usability.

• Work closely with interdisciplinary teams to ensure solutions are scientifically sound, applicable, and impactful.

• Contribute to broader initiatives such as biological read-across, reverse translation, and digital workflow enhancements.

Must-Have Qualifications:

• PhD or MSc (with relevant experience) in Computational Toxicology , Cheminformatics , Bioinformatics , Pharmacology , or a related field.

• Proven experience developing machine learning models applied to chemical and/or biological data.

• Strong background in cheminformatics , including familiarity with molecular descriptors, chemical similarity, and structure-based analysis.

• Hands-on experience with toxicological datasets and endpoints (e.g., liver or kidney toxicity).

• Proficient in Python or R , and commonly used libraries (e.g., RDKit, scikit-learn, Pandas, TensorFlow).

• Excellent collaboration and communication skills, with the ability to present complex data clearly to interdisciplinary teams.

Nice to Have:

• Experience with omics data integration or biological pathway modeling in toxicology.

• Familiarity with pharmaceutical R&D or previous experience in an industry setting.

• Interest in expanding predictive models to novel data types and experimental readouts.