AIRx Director, Computational & AI Biologics Design Lead
About the role
The Computational & AI Biologics Design Lead plays a critical role in Takeda's Lab of Tomorrow, focusing on in silico biologics design and AI-enabled biologics discovery. Reporting to the Head of AIRx, this role is integral to the Takeda Boston (TBOS) Large Molecule Pod.
Responsibilities
Define and drive computational design strategy for large-molecule programs, including antibody, VHH, and multispecific or fusion formats, from early format selection through lead optimization.
Design and prioritize molecular candidates using generative AI/ML and computational modeling approaches.
Partner with the Biologics Discovery Lead to translate computational proposals into testable engineering priorities.
Integrate structural biology data into design strategies to inform format selection, epitope targeting, and interface optimization.
Oversee virtual screening, binding affinity prediction, and developability risk assessment for candidate sequences.
Collaborate with translational and DMPK scientists to model PK/PD behavior, TMDD, and species cross-reactivity in silico.
Define and steward data requirements for AI model training within the pod, including structure data from experimental campaigns, annotation standards, and integration with Takeda’s data infrastructure.
Guide development and refinement of computational workflows to enable pod scalability, speed, and reproducibility across the DMTA cycle.
Act as a hands-on computational authority within pod governance, preparing and presenting in silico analyses for PRC reviews, design review boards, and candidate declaration milestones.
Interface with Takeda’s discovery automation capabilities to define assay and data readout specifications for pod programs entering automated workflows when applicable.
Maintain deep subject-matter expertise by staying current with advances in AI for biologics design and structure prediction, translating emerging capabilities into actionable proposals for the pod.
Represent Takeda’s computational biologics capabilities in interactions with external partners, at conferences, and in the scientific community.
Requirements
PhD in Computational Biology, Bioinformatics, Structural Biology, Computer Science, or a closely related discipline.
10+ years of drug discovery experience with a demonstrated track record of computational impact on large-molecule or biologics programs; industry experience strongly preferred.
Deep expertise in antibody and protein sequence, structure, and function modeling, with proficiency in generative or predictive AI frameworks applied to biologics design.
Broad proficiency in computational tools relevant to biologics, spanning structural analysis, molecular simulation, developability prediction, and bioinformatics.
Strong coding skills (Python required); experience building and deploying ML models in a drug discovery context; familiarity with cloud-based compute and MLOps practices.
Demonstrated ability to operate as both a technical individual contributor and a cross-functional scientific partner in a fast-paced, program-driven environment.
Versatile communicator: able to present complex computational findings to biologists, clinical scientists, and senior leadership with clarity and scientific rigor.
Qualifications
Experience with multispecific antibody formats and the associated engineering, developability, and PK/PD considerations.
Experience integrating physics-based modeling with deep learning approaches to improve prediction accuracy and generalization.
Prior experience defining data requirements and governance for AI/ML platform development across multiple programs or sites.
Experience operating within or alongside an external AI design partner environment, including co-design workflows and campaign-level data return.
Track record of contributing to IND-enabling programs; familiarity with candidate declaration criteria and biologics CMC considerations.