Senior/Staff Scientist, Cheminformatics & Data Science

Deep Origin is seeking a Senior or Staff Scientist with strong expertise in cheminformatics, machine learning, and drug discovery to join a groundbreaking initiative funded by ARPA-H. This is a rare opportunity to help define and deploy scalable computational models for predicting protein-ligand binding, enabling next-generation therapeutics.

You’ll work with a multidisciplinary team of scientists and engineers to lead ligand- and structure-based modeling efforts, contribute to data curation, and develop high-performing predictive models that accelerate molecular design.

Requirements

• Ph.D. in cheminformatics, computational chemistry, chemical biology, or a related field;
• 2+ years of industry experience in drug discovery or pharmaceutical data science;
• Deep familiarity with protein-ligand interactions, protein structure handling, and ligand representations;
• Strong proficiency in Python, with hands-on experience using RDKit, scikit-learn, PyTorch, or similar frameworks;
• A strong foundation in ML model development, validation, and interpretability.

Nice to have:

• Experience working with DNA-encoded libraries datasets, including data quality control and preprocessing;
• Exposure to protein structure analysis, scoring functions, or ligand docking workflows (e.g., AutoDock Vina, etc.);
• Familiarity with cloud platforms (AWS, GCP) and workflow orchestration tools.

Responsibilities:

• Design, curate, and process diverse chemical and biological datasets (ChEMBL, BindingDB, RCSB PDB, UniProt, etc.);
• Build and evaluate ligand-based ML models (e.g., QSAR) using methods like gradient-boosted trees, neural nets, and graph neural networks (GNNs);
• Incorporate structural features of proteins and ligands into affinity prediction workflows;
• Collaborate closely with medicinal chemists, biologists, and data scientists to support data-driven discovery decisions;
• Plan and organize work to meet key deadlines and milestones; coordinate with collaborators to ensure integration with broader project efforts;
• Communicate effectively within Deep Origin and with external partners, regularly sharing updates on progress, blockers, and decisions;
• Clearly communicate model performance, limitations, and insights to both technical and non-technical teams.

Why Join Deep Origin

Deep Origin builds cloud-native tools for scientists working on the frontiers of biology, chemistry, and computation. We’re mission-driven and deeply collaborative, your work will directly impact how therapeutics are discovered and optimized. As part of this ARPA-H initiative, you'll have the opportunity to operate at the cutting edge of scientific infrastructure and translational impact.

We offer:

• A remote-friendly environment (with hubs in the US and Armenia);
• Competitive compensation and equity packages;
• Flexible schedules;
• A culture that encourages curiosity, autonomy, and creative problem-solving.

Apply now and help accelerate the future of therapeutic discovery.