Principal Computational Chemist

About the Role

As Principal Computational Chemist, you’ll lead the end‑to‑end design of novel small‑molecule therapeutics using AQEMIA’s computational platform (generative AI, physics‑based methods). You’ll operate at the intersection of cutting‑edge algorithms, molecular simulations, and medicinal chemistry.

Responsibilities

• Computational Drug Design: Design and optimize small molecules targeting specific therapeutic areas by leveraging AQEMIA’s drug design engine. Systematically model ADME, toxicity, and selectivity properties.
• Communication: Clearly present and communicate findings to stakeholders at all levels and across functions, ensuring conclusions are robust and data‑driven.
• Technology Application: Apply and validate AQEMIA’s baseline technologies, including generative AI algorithms and physics‑based methods, to accelerate drug discovery.
• Feedback and Improvement: Offer systematic feedback on the platform, driving continuous improvement and enhancing technological capabilities.
• Innovation and Advocacy: Proactively propose and implement new approaches to advance Drug Discovery programs, improving accuracy, speed, and scalability.
• Interdisciplinary Collaboration: Collaborate with machine learning engineers, project managers, medicinal chemists, and physicists.
• Mentoring & Technical Leadership: Mentor junior computational chemists, lead by example in rigor, reproducibility, and scientific communication, and contribute to hiring and team development.

Qualifications

• Industry experience: at least 10 years in pharmaceutical, biotech, or CRO companies, focusing on computational chemistry for small‑molecule drug discovery.
• Deep expertise in structure‑based and ligand‑based drug design: homology modeling, docking, SAR analysis, virtual screening, pharmacophore design, QSAR, ADMET property modeling, multi‑parameter optimization.
• Drug discovery contributions: proven success in advancing compounds from hit identification to pre‑clinical candidates.
• Target experience: kinases, GPCRs, phosphatases, ion channels, bromodomains.

Technical Skills

• Strong experience in structure‑based drug design and ligand‑focused techniques such as protein homology modeling, docking, pharmacophore hypothesis generation, virtual screening, SAR analysis.
• QSAR and ADMET property modeling, multi‑property optimization‑based compound design, and physics‑based methods (FEP, MD, MM/GBSA).
• Familiarity with computational chemistry/cheminformatics packages (e.g., RDKit, OpenMM, OpenFE, CCDC).
• Extensive knowledge of structural biology.
• Solid understanding of medicinal chemistry principles and computational methods for optimizing drug properties.
• Ability to analyze chemical data and identify trends using statistical methods to ensure reproducibility and data‑driven decision‑making.
• Proficiency in Python in Linux/UNIX environments.

Nice‑to‑Have

• Prior experience with generative AI methods in drug discovery.
• Experience optimizing or evaluating generative models (assessing chemical diversity, evaluating model‑generated molecules for quality/novelty, training/fine‑tuning generative architectures).
• Familiarity with co‑folding algorithms: experience integrating structural predictions into computational design workflows.

Additional Information

QCEMIA currently offers visa sponsorship only for Paris‑based roles. Applications will be accepted until 1 May. After that date the role will be considered closed.