Scientist II/Senior Scientist, Computational Chemistry, Drug Discovery

About the role

You will monitor and review drug discovery agents' computational chemistry workflows, recommendations, and optimization plans for scientific and chemical validity on a daily basis. You will evaluate agent-generated drug discovery plans that combine chemistry, biophysics, cofolding, simulation, assay, and low-data model outputs, and determine whether the resulting optimization strategy is scientifically coherent for current projects. You will advise on compound prioritization across discovery programs, including tradeoffs between potency, selectivity, developability, uncertainty, and experimental feasibility in a fast-paced environment. You will define which computational chemistry tools agents should use, when they should use them, what inputs are required, and how outputs should be interpreted to ensure scientific rigor. You will lead computational chemistry strategy for live drug discovery programs when needed, including hypothesis generation, modeling plans, compound prioritization, and interpretation of results with clear documentation. You will build, adapt, or guide the creation of open-source-first workflows for docking, virtual screening, SAR analysis, conformer generation, pharmacophore modeling, QSAR, ADMET and property modeling, and cheminformatics to support agent workflows. You will apply protein-ligand binding modeling to support hypothesis generation, compound design, and prioritization while ensuring that all recommendations are traceable and scientifically defensible. You will partner with medicinal chemists, biologists, computational biophysicists, cofolding and low-data ML scientists, and research engineers to improve AI-assisted discovery loops and integrate computational insights.

Key facts

What you'll do

• Monitor and review drug discovery agents' computational chemistry workflows, recommendations, and optimization plans for scientific and chemical validity.
• Evaluate agent-generated drug discovery plans that combine chemistry, biophysics, cofolding, simulation, assay, and low-data model outputs, and determine whether the resulting optimization strategy is scientifically coherent.
• Advise on compound prioritization across discovery programs, including tradeoffs between potency, selectivity, developability, uncertainty, and experimental feasibility.
• Define which computational chemistry tools agents should use, when they should use them, what inputs are required, and how outputs should be interpreted.
• Lead computational chemistry strategy for live drug discovery programs when needed, including hypothesis generation, modeling plans, compound prioritization, and interpretation of results.
• Build, adapt, or guide the creation of open-source-first workflows for docking, virtual screening, SAR analysis, conformer generation, pharmacophore modeling, QSAR, ADMET and property modeling, and cheminformatics.
• Apply protein-ligand binding modeling to support hypothesis generation, compound design, and prioritization.
• Partner with medicinal chemists, biologists, computational biophysicists, cofolding and low-data ML scientists, and research engineers to improve AI-assisted discovery loops.
• Evaluate agent-generated molecular design ideas and identify when proposed chemistry, binding hypotheses, or optimization strategies are weak or unsupported.
• Help establish validation standards, review protocols, and guardrails for computational chemistry tools used by AI systems.
• Translate computational chemistry judgment into practical requirements for agent tools, workflows, benchmarks, and decision criteria.
• Conduct iterative analysis of agent proposals against historical assay data, chemical feasibility, and project priorities to refine guidance.
• Synthesize complex modeling results into concise recommendations that balance scientific depth with actionable decision-making.
• Track emerging methods in AI-driven chemistry and assess their applicability to current drug discovery challenges.
• Contribute to internal documentation and tool design that enhances agent reliability and scientific transparency.
• Participate in cross-functional discussions to align computational strategies with biological and experimental realities.
• Provide hands-on support for urgent modeling needs during active discovery campaigns.
• Mentor junior scientists on best practices in computational chemistry and agent evaluation.
• Ensure that all modeling assumptions are explicitly stated and that limitations are clearly communicated to stakeholders.

Requirements

• PhD or equivalent experience in computational chemistry, chemistry, cheminformatics, molecular modeling, biophysics, or a related field.
• Strong practical experience applying computational chemistry in a drug discovery context, including active program support or leadership.
• Demonstrated history of modeling protein-ligand binding and using those models to inform discovery decisions.
• Working knowledge across docking, virtual screening, SAR modeling, conformer generation, pharmacophore modeling, QSAR, ADMET or property prediction, and cheminformatics.
• Strong medicinal chemistry experience and the ability to reason about compound optimization, SAR, developability, and synthetic or experimental tradeoffs.
• Fluency in Python and hands-on experience building open-source computational chemistry workflows with libraries such as RDKit, Biopython, OpenMM, MDAnalysis, or comparable tools.
• Ability to evaluate computational recommendations critically and communicate uncertainty, assumptions, and limitations clearly.
• Comfort working alongside AI systems, including reviewing, guiding, and improving agent-generated plans rather than treating them as final outputs.