Principal Scientist of AI-Driven Protein design

Position SummaryAntibody AIDD (Principal Scientist) is responsible for leading a computational science team focused on biologics discovery. This role will provide critical support for the discovery and engineering of antibodies, fusion proteins, and other large-molecule therapeutics by applying and developing cutting-edge computational biology, structural biology, and AI technologies. The leader must be a technical expert capable of leading a team and collaborating closely with experimental teams in antibody engineering and protein sciences to solve core challenges in affinity, specificity, stability, and developability.Key ResponsibilitiesTeam Leadership & Management: Lead and develop a team of 2-4 computational biologists, fostering a scientifically rigorous and collaborative work environment.Project Scientific Leadership: Serve as the core computational lead for biologics projects, directing the formulation and execution of computational strategies, including computational antigen design, antibody/protein design and optimization, and epitope prediction.Developability Assessment: Lead the team in establishing and applying high-throughput computational predictive models to systematically assess and optimize the developability of candidates (e.g., immunogenicity, aggregation, viscosity) at early discovery stages to de-risk downstream development.Technology Innovation & Platform Development: Track the latest advances in AI for biologics design; lead the development and validation of new algorithms and workflows for protein design, structure prediction, and property prediction, and promote their deployment on internal platforms.Cross-Functional Collaboration: Collaborate closely with teams in Antibody Discovery, Protein Sciences, Bioanalytics, and Formulation Development to form an efficient "design-build-test-learn" R&D cycle.Basic QualificationsPh.D. in Computational Biology, machine learning, Structural Biology, Biophysics, or a related field.5+ years of experience in biologics R&D within the pharmaceutical or biotechnology industry.Excellent programming skills in Python or R and experience with relevant bioinformatics and structural biology software.A solid theoretical and practical foundation in protein structure modeling and molecular dynamics simulations.QualificationsStructural Modeling & De Novo Design: Deep expertise in protein structure prediction (e.g., AlphaFold2/Multimer), protein-protein docking, and loop modeling.Biophysics Simulation: Advanced knowledge and practical experience in running and analyzing all-atom molecular dynamics (MD) simulations of complex biologics (e.g., antibodies, bispecifics) to assess dynamics, stability, and aggregation propensity.AI for Biologics: Familiarity and hands-on experience with modern AI methods, such as Protein Models (e.g., ESMFold, ProGen).Diffusion- or Generative Models: Experience applying diffusion- or generative models for protein sequence and structure design.Graph Neural Networks (GNNs): Knowledge of GNNs for protein function prediction or developability assessment.Bioinformatics & Multi-Omics Integration: Proficiency in advanced sequence analysis, structural bioinformatics, and experience integrating multi-omics data (e.g., genomics, proteomics) for target identification and validation.Breadth & Depth of Project Experience: A proven track record of leading computational efforts for antibody de novo design and affinity maturation.Verifiable contributions to solving specific developability issues for multiple biologic formats (e.g., mAbs, VHHs, bispecifics, ADCs). #J-18808-Ljbffr

Created: 2025-09-17