Postdoc on cofolding models for In-Silico Drug Discovery

Postdoctoral position in computational drug discovery focused on developing and optimizing cofolding models for structure-based drug design. The role involves dataset curation, model fine-tuning, performance evaluation, and integration of AI/ML approaches into discovery workflows within a multidisciplinary research environment.

Responsibilities

• Design, execute, and analyze fine-tuning experiments for cofolding and structure-prediction models with benchmarking
• Generate, curate, and manage training datasets including complex structures and molecular dynamics ensembles
• Evaluate model performance using structural and task-relevant metrics to establish evaluation best practices
• Integrate fine-tuned models into end-to-end discovery workflows with inference, reporting, and documentation
• Collaborate with computational, CADD, biologics, and AI/ML scientists to align research with drug-discovery objectives

Requirements

• PhD in computational chemistry, structural bioinformatics, computational biology, or machine learning on biomolecular systems
• Strong knowledge of protein structure and structure-based modeling principles
• Experience with AI/ML model development, training, fine-tuning, and evaluation using frameworks like PyTorch
• Experience generating or curating structural datasets including protein complexes and molecular dynamics data
• Python programming proficiency for research workflow development
• Familiarity with HPC and GPU computing environments
• First-author peer-reviewed publications and presentations at major scientific meetings required

Compensation: €60,000.00–€96,255.00 base