About the job

You will be one of the first dedicated data hires at InCycling: a Berlin-based startup building AI-driven infrastructure for surplus chemical trading in a highly regulated industry. This role starts in cheminformatics and chemical data science, but as the platform grows, you'll have the opportunity to expand to Python software engineering, machine learning engineering, or data engineering, if it suits your interests.

Tasks

In this role you will:

• Build Python-based data pipelines to work with complex chemical data;


• Incorporate into our workflow public databases, pre-trained domain-specific models, and OSS tools (e.g. ChemBERTa, RDKit, DeepChem);


• Develop semantic embeddings; create augmented and synthetic chemical data; perform analysis, classification, and interpretation of chemical records;


• Parse and extract structured data from unstructured sources:...