Head of Machine Learning Research (all genders)

Job description

Zur Jobsuche Startseite Stellenangebot: Head of Machine Learning Research (all genders) bei Bayer AG Pharmaceuticals Das Wichtigste im Überblick Besondere Merkmale Arbeitsort Berlin Angebotsart Arbeit Anstellungsart Vollzeit Beginn ab sofort Berufsbezeichnung Machine Learning Engineer Info zur Bewerbung Vormerken Notiz / Status Notiz hinzufügen Bitte anmelden, um diese Funktion zu nutzen. Bewerbungsstatus hinzufügen Bitte anmelden, um diese Funktion zu nutzen. PDF / Drucken Teilen Veröffentlichungsdatum: Vor 8 Tagen veröffentlicht Änderungsdatum: Vor 2 Tagen bearbeitet Stellenbeschreibung At Bayer we’re visionaries, driven to solve the world’s toughest challenges and striving for a world where ,Health for all, Hunger for none’ is no longer a dream, but a real possibility. We’re doing it with energy, curiosity and sheer dedication, always learning from unique perspectives of those around us, expanding our thinking, growing our capabilities and redefining ‘impossible’. There are so many reasons to join us. If you’re hungry to build a varied and meaningful career in a community of brilliant and diverse minds to make a real difference, there’s only one choice. Head of Machine Learning Research (all genders) We are seeking a scientific and technical leader to make AI & machine learning central to how we design and optimize molecules across our discovery portfolio. You will sit on the Data Science & AI leadership team and be accountable for the models, platforms, and ways of working that shorten design-make-test-analyze cycles and raise our probability of delivering high-quality candidates. This is a hands-on strategy role, not research-only or delivery-only. You will set a multi-year technical roadmap, build and lead a team of 25, and be measured by whether project teams make better decisions and reach candidate faster because of the capabilities you build. It demands fluency in both modern AI/ML and the medicinal chemistry and structural biology realities of drug discovery — expect to spend as much time in project reviews as in model architecture discussions. YOUR TASKS AND RESPONSIBILITIES You define and deliver an AI/ML molecular design strategy aligned with current and future Drug Discovery priorities You make rigorous build/buy/partner decisions for generative design, property prediction, structure-based ML, synthesis planning, foundation models, and external platforms You establish robust model-validation standards, including prospective benchmarking, uncertainty quantification, applicability domains, reproducibility, and transparent reporting of limitations You monitor the external AI/ML landscape, identify disruptive developments early, and secure access to best-in-class capabilities You embed ML into live discovery programs by partnering closely with medicinal chemistry, computational design, structural biology, biophysics, screening, DMPK, safety, and Drug Discovery Sciences You co-own program outcomes from hit identification through candidate nomination, optimizing potency, selectivity, ADMET, developability, synthetic feasibility, and IP position You lead development of core platforms for ADMET/property prediction, generative and de novo design, retrosynthesis, synthetic accessibility, co-folding, pose prediction, docking rescoring, and ML-accelerated free-energy methods You build a scalable data and MLOps foundation with curated and harmonized assay, structural, and DMTA data; ensuring provenance, feedback capture, versioning, monitoring, documentation, and reproducibility You lead and develop a high-performing interdisciplinary organization; managing strategic investments and external partnerships while fostering scientific excellence, collaboration, and measurable portfolio value WHO YOU ARE You hold a PhD in computational chemistry, cheminformatics, structural biology, biophysics, computer science, or a related field, with demonstrated depth in both molecular science and machine learning. Exceptional MSc candidates with equivalent experience will be considered You bring extensive relevant experience, including strong exposure to leading technical teams; experience leading leaders is strongly preferred You have experience in a large matrixed pharma R&D organization, or scaling a capability from startup to enterprise You possess deep, current expertise in ML for molecules: graph neural networks, transformers, generative methods (diffusion, flow matching, autoregressive), Bayesian optimization and active learning, transfer learning on sparse assay data, and uncertainty quantification You have a working command of the discovery domain: SAR interpretation, multi-parameter optimization, ADMET and developability, protein structure and ligand binding, docking and free energy methods You demonstrate impact on real programs, with advanced molecules, cycles shortened, and decisions changed, a publication record alone is not sufficient You have the credibility to partner with medicinal chemists and structura