SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Lila Sciences is seeking a Scientist II/Senior Scientist in Computational Chemistry to bridge AI-driven drug discovery workflows with practical chemical expertise. You will evaluate, guide, and improve AI agent-generated optimization plans, compound prioritizations, and modeling workflows to ensure they are scientifically sound and chemically sensible. This role combines critical oversight of agentic systems with hands-on leadership of live drug discovery programs when needed.
Key responsibilities include: monitoring and reviewing computational chemistry workflows generated by AI agents for scientific validity; evaluating multi-disciplinary optimization strategies combining chemistry, biophysics, simulation, and low-data ML outputs; advising on compound prioritization across discovery programs, balancing potency, selectivity, developability, and experimental feasibility; defining which computational tools agents should use and how to interpret outputs; leading computational chemistry strategy for active drug programs including hypothesis generation and modeling plans; building or adapting open-source workflows for docking, virtual screening, SAR analysis, conformer generation, pharmacophore modeling, QSAR, ADMET prediction, and cheminformatics; applying protein-ligand binding models to support design and prioritization; partnering with medicinal chemists, biologists, computational biophysicists, and ML scientists; identifying weaknesses in agent-generated molecular design ideas; establishing validation standards and guardrails for computational tools; and translating chemical judgment into practical requirements for agent systems.
You will need a PhD or equivalent in computational chemistry, chemistry, cheminformatics, molecular modeling, biophysics, or related field, with strong practical experience applying computational chemistry in drug discovery contexts. Required expertise spans docking, virtual screening, SAR modeling, conformer generation, pharmacophore modeling, QSAR, ADMET prediction, and cheminformatics. You must have demonstrated experience modeling protein-ligand binding and using those models to inform discovery decisions, strong medicinal chemistry knowledge, fluency in Python, and hands-on experience building workflows with RDKit, Biopython, OpenMM, MDAnalysis, or comparable tools. Critical skills include the ability to evaluate computational recommendations with clear communication of uncertainty and limitations, comfort working alongside and improving AI agent outputs, and strong cross-functional collaboration across chemistry, biology, ML, and engineering teams.
