Director, Head of Computational Design

Role Summary

The Director, Head of Computational Design is accountable for the design and application of new advanced computational methods, including Large Language Models (LLMs) and AI, for cutting-edge mRNA design and next-generation vaccine and platform design and development. This role guides the design and optimization of nucleic acid therapeutics (e.g., mRNA), associated vaccine platforms and delivery systems, and provides in silico solutions spanning structural bioinformatics, molecular modeling, and AI/ML-driven design. It supports discovery and preclinical research, translational, and early clinical stages, and leads a world-class team to ensure scientific excellence and alignment with program leaders.

Responsibilities

• Provides strategic vision and leadership for computational molecular design initiatives within VIDRU Data Sciences, focusing on next generation mRNA design, vaccine, antigen and NLP platform development.
• Leads and manages a multidisciplinary team of computational design scientists, fostering high performance, scientific innovation, and ongoing professional development.
• Directs the development and application of advanced computational design methodologies, including structural bioinformatics, molecular modeling, and protein/nucleic acid engineering, with emphasis on mRNA sequence and structure optimization.
• Drives the leveraging of AI and LLMs for de novo design, optimization, and predictive modeling of antigens, mRNA, LNPs, adjuvants, and monoclonal antibodies/ADCs.
• Ensures scientific integration by embedding computational design experts within discovery project teams, providing data science expertise from early-stage research through candidate selection and optimization.
• Integrates computational predictions with experimental validation via active learning loops, linking with DiscoTech laboratories to accelerate design and optimization cycles.
• Establishes collaborative links with DPLs, VDLs, PILs, TPLs and clinical sciences teams to ensure computational insights inform pipeline progression.
• Drives innovation in computational design analytics by partnering with AIML and R&D Tech divisions and external KOLs, exploring novel AI/ML methods and computational paradigms.

Qualifications

• Required: PhD or equivalent experience in Computational Biology, Data Science, Mathematics and Physics, Biological or Chemical Engineering, Bioinformatics, Computational Life Sciences or equivalent; deep theoretical background and practical experience in quantitative sciences applied to biology; strong computer science competencies; research experience with publications in relevant areas; 8+ years of scientific experience including four years of direct/matrix people management and international leadership responsibilities; demonstrated ability to lead cross-functional teams and serve as a global reference for the function.
• Preferred: Demonstrated publication record in advanced molecular modelling and simulation, structural bioinformatics and protein engineering for antigen/vaccine design, and application of AI/LLMs for de novo mRNA design and predictive modelling; experience in nucleic acid-based therapeutics design and their delivery platforms; predictive modelling for molecular stability, expression, and immunogenicity; chemoinformatics and rational drug design principles; experience with high-performance computing for large-scale projects; experience with active learning frameworks for experimental design.

Skills

• Advanced molecular modelling and simulation (e.g., molecular dynamics, docking, free energy calculations)
• Structural bioinformatics and protein engineering for antigen/vaccine design
• Application of AI and LLMs for de novo mRNA design and optimization
• Computational design of nucleic acid-based therapeutics and delivery platforms
• Predictive modelling for stability, expression, and immunogenicity
• Chemoinformatic and rational drug design principles
• High-performance scientific computing infrastructures for large-scale projects
• Active learning frameworks for experimental design and optimization
• Cross-functional collaboration and leadership