Principal Scientist – Cheminformatics & Data Science
Orion Pharma Näytä kaikki työpaikat
- Espoo, Helsinki
- Vakituinen
- Täyspäiväinen
- Drive best practices in cheminformatics, including molecular representations, descriptors, fingerprints, and QSAR methodologies
- Ensure modeling approaches are interpretable, reliable, and relevant for decision-making
- Identify and develop novel cheminformatics methods with clear impact on drug discovery
- Define and implement standards for reproducible modeling, data quality, and workflow design
- Ensure consistency and robustness across chemical and biological data analysis
- Provide transparent assessments of model performance, limitations, and uncertainty
- Design and implement scalable, production-ready workflows for virtual screening, library design, and data analysis
- Develop tools and pipelines that enable self-service data access and analysis for scientists
- Ensure integration with enterprise platforms (e.g., LiveDesign) and internal infrastructure
- Lead the cheminformatics and data science domain without direct reports
- Guide a subgroup of data platform specialists and MLOps experts
- Influence technical direction across the unit through scientific credibility and expertise
- Work closely with computational scientists and project teams to align data science approaches with scientific needs
- Translate complex scientific questions into robust computational strategies
- Contribute to external scientific visibility through publications, open-source development, and collaborations
- A scientifically ambitious environment with top-tier professionals
- A unique opportunity to shape how cheminformatics and data science are applied at scale in drug discovery
- Access to modern computational infrastructure and data platforms
- Competitive salary, comprehensive benefits, and support for relocation
- PhD in cheminformatics, computational chemistry, data science, or a related field
- Significant experience applying cheminformatics and data science methods in an industrial drug discovery setting
- Strong expertise in:
- molecular representations, descriptors, and fingerprints
- QSAR and ligand-based modeling approaches
- chemical and biological data handling
- Strong programming skills in Python and relevant libraries (e.g., RDKit, NumPy, pandas, scikit-learn)
- Experience with:
- SQL and data engineering concepts
- HPC environments and Linux
- workflow tools and reproducible computation
- APIs and modern data infrastructure
- Ability to define best practices and influence technical direction without formal authority
- Strong communication skills and ability to explain complex concepts to multidisciplinary teams
- Fluent written and spoken English