Job Description
Job Summary:
- We are seeking a highly motivated Cheminformatics Scientist to design, evaluate, and build end-to-end small molecule computational workflows within the client platform.
- This role requires strong hands-on expertise in state-of-the-art computational methods across the drug discovery pipeline, from virtual screening to lead optimization.
- You will work at the intersection of cheminformatics, physics-based modeling, and machine learning, partnering closely with client software engineering and ML teams to deliver scalable, production-grade workflows.
- This is a high-impact contract role, where you will be expected to independently evaluate tools, make build-vs-buy decisions, and deliver robust workflow solutions.
Duties and Responsibilities:
End-to-End Workflow Development:
- Design and implement workflows spanning:
- Virtual screening (ligand-based and structure-based).
- Hit identification and hit expansion.
- Hit-to-lead selection.
- Lead optimization.
Method Development & Application:
- Apply and integrate core computational chemistry and cheminformatics methods, including:
- Ultra-large library search:
- Substructure search.
- Fingerprint and embedding-based similarity search.
- Shape and pharmacophore-based screening.
- Molecular enumeration:
- Reaction-based enumeration.
- Fragment-based design and expansion.
- Ligand-based modeling:
- QSAR, similarity, clustering, active learning loops.
- Structure-based modeling:
- Docking, rescoring, pose prediction, structure-aware search.
- Physics-based methods:
- Molecular dynamics (MD).
- Free energy perturbation (FEP) and related approaches.
Cross-functional Collaboration:
- Partner with:
- Machine Learning teams to integrate predictive and generative models.
- Software Engineering teams to productionize workflows and ensure scalability.
- Scientific stakeholders to align workflows with drug discovery needs.
Required Qualifications:
- PhD or MS in Cheminformatics, Computational Chemistry, Medicinal Chemistry, or related field.
- Strong understanding of small molecule drug discovery workflows.
- Demonstrated expertise in:
- Substructure and similarity search (fingerprints, graph-based, embedding-based).
- Shape and pharmacophore searching.
- Reaction-based and fragment-based enumeration.
- Docking and structure-based design.
- QSAR and ligand-based modeling.
- Active learning and iterative design strategies.
- Physics-based simulations (e.g., MD, FEP).
- Hands-on experience with tools such as:
- RDKit, OpenEye, or equivalent.
- Docking platforms (e.g., Glide, AutoDock, GOLD).
- Strong programming skills in Python.
Preferred Qualifications:
- Experience working with ultra-large chemical libraries (e.g., Enamine REAL, WuXi Galaxy).
- Familiarity with generative chemistry approaches (SMILES-, graph-, or diffusion-based models).
- Experience integrating ML models into production workflows.
- Experience with workflow orchestration tools (e.g., Airflow, Nextflow).