Forward-Deployed Cheminformatician

Own how binding data is prepared across co-folding focused networks and initiatives. Binding data arrives from pharma partners in heterogeneous shapes — different assay registries, metadata, chemical-representation standards, and qualifiers. You will define a repeatable, well-documented preparation pipeline that pharma representatives can run alongside Apheris, and scale it to the public-data corpus for model training. This is half engineering, half forward-deployed work.

What you'll do

• Define and own the binding-data preparation protocol — data schema, small-molecule standardization, assay metadata model, value handling (KD, Ki, IC50, pIC50), qualifier and censored-value handling, duplicate and replicate aggregation.
• Build the tooling that runs it — modular scripts, validators with actionable errors, and reusable pipelines that survive different pharma upstream systems (Dotmatics, Spotfire, in-house registries).
• Work forward-deployed with pharma. Sit with their biologists and medicinal chemists, walk them through the protocol, sense-check what an assay column actually measures, and unblock retrieval.
• Maintain the small-molecule representation pipeline — RDKit standardization, tautomer and ionization handling, stereochemistry preservation, and PAINS / frequent-hitter filtering.
• Curate the public binding-data foundation — ChEMBL, BindingDB, PubChemBioAssay — prepared to the same standard for model training.
• Hand the productized pipeline cleanly to engineering for scaling, and partner with ML to keep the data contract valid as models and networks evolve.

What you'll need

• BSc, MSc, PhD or equivalent in cheminformatics, computational chemistry, or a related field, plus 3+ years preparing biological assay data in a discovery setting.
• Fluent in Python and RDKit. SMILES normalization, tautomer / ionization / stereochemistry handling, and scaffold extraction are second nature.
• Hands-on experience curating quantitative binding assay data (KD, Ki, IC50, pIC50) and HTS data — censored values, qualifiers, duplicates, replicate aggregation, and assay metadata interpretation.
• Write good engineering code — version control, tested modular scripts, validators that return useful errors.
• Comfortable forward-deployed with pharma medicinal chemists and biologists. Can interpret column labels and encode that back into the protocol.
• Enjoy turning a messy ad-hoc cleaning job into a repeatable protocol others can run.

Nice to have

• Practical familiarity with public binding-data sources (ChEMBL, BindingDB, PubChemBioAssay) and the gotchas in each.
• Applied LLM tooling (Claude, Codex, Cursor) to accelerate data cleaning or metadata harmonization.
• Worked across institutional data boundaries — federated, multi-party, or otherwise — where the data-preparation contract has to hold under partial visibility.
• Publication record or open-source contributions in cheminformatics or quantitative pharmacology.

What they offer

• Industry-competitive compensation, including early-stage virtual share options
• Remote-first work
• Wellbeing budget, mental health support, work-from-home budget, co-working stipend, and learning budget
• Generous holiday allowance
• Office Days at Berlin HQ or different European location (3x per year)