Senior Director, Computational Drug Discovery; DK

Does it excite you to work with computational and AI methods at the forefront of multi-modality drug discovery? And do you have experience leading computational scientists and applying structure-based design, machine learning, and generative modeling to real pipeline decisions? If this sounds like you, and you are ready to take on a broad area of responsibilities, then you could be our new colleague.

As Senior Director, Computational Drug Discovery, you will mentor and grow a global team across two sites — Cambridge, USA and Copenhagen, DK — setting the vision and driving the computational strategy to support Zealand's multi-modal pipeline including peptides, small molecules and antibodies. Partnering closely with Molecular Platform and Medicinal Chemistry teams, you will build the people, processes and advanced computational methods needed to strengthen in-silico validation of hypotheses and prioritize the molecules that get synthesized and tested.

We offer exciting responsibilities:

• Build, mentor, and grow a world-class team across Copenhagen, DK and Cambridge, USA, investing in the development of computational scientists while working side by side with medicinal chemists, protein engineers, structural biologists, molecular pharmacologists, Pharm Dev, and DMPK to ensure that computational science meaningfully shortens the time from concept to development candidate
• Serve as Chemistry Lead or Research Project Leader (RPL) for one or more programs and contribute computational leadership across the wider research portfolio
• Contribute to target evaluation, modality selection, and portfolio prioritization, bringing a computational lens to whether a target is tractable and with what
• Guide your team's contributions to ensure robust progression of candidates, applying clear understanding of pharmacology, pharmacokinetics, ADME, immunogenicity, and develop ability, including computational input into DMPK risk and CMC-relevant properties
• Contribute to Zealand's Research AI strategy and execution, building and contributing to FAIR data foundations, MLops and reproducible scientific computing, LLM integration and agentic orchestration and evaluation, and evaluation, training and deployment of domain specific foundation models
• Curate strategic academic, biotech, and tech collaborations to keep Zealand at the forefront of innovation in computational chemistry and biologics design
• Represent Zealand at conferences, consortia, and external innovation forums, and publish where it serves the science and the company's goals
• Contribute to business development and licensing efforts where computational and chemistry diligence is required, including assessment of in-licensing candidates, platform technologies, and partnership opportunities

You are an inclusive, collaborative leader who combines deep quantitative expertise in drug discovery with strategic portfolio and pipeline focus, and the ability to tactically integrate emerging and classical methods to develop innovative fit-for-purpose solutions. You can lead a diverse team of computational scientists and influence and engage with broad functional teams across geographies.

You have a Ph.D. (or equivalent advanced degree) in Computational Chemistry/Biology/Structural Biology or a relevant life sciences discipline, with 10+ years of biopharma R&D experience. As a technical leader, you bring credibility to guide and coach your team through hands-on expertise in at least two of the following areas:

• Structure prediction & modeling: co-folding and structure prediction, homology and complex modeling, and integration with experimental cryo-EM and X-ray data, with rigorous evaluation of confidence metrics and their limitations, applied to antibody (CDR-loop prediction, paratope/epitope analysis) and peptide/macrocyclic design, as well as target assessment and draggability
• Structure and ligand-based drug design: docking and physics-based modeling (MD, FEP/TI, QM/MM) for relative and absolute binding, with rigorous understanding of the applicability domains of different methods and how to combine approaches where any single method falls short, plus…