Computational Biologist Principal Research Scientist II

Job Description

Position Overview

We are seeking an accomplished scientific leader in AI-enabled computational biology to establish and advance next-generation immunogenicity and translational immunology capabilities across biologics discovery and development. The successful candidate will serve as a discipline expert and strategic partner, combining machine learning, protein language models, structural modeling, systems immunology, and computational biology to predict, understand, and mitigate anti-drug antibody (ADA) responses and other immune-mediated liabilities across therapeutic proteins, multispecific antibodies, antibody-drug conjugates, gene therapies, and novel modalities.

This individual will define scientific strategy, lead high-impact cross-functional programs, build fit-for-purpose computational capabilities, and translate complex analyses into clear recommendations for project teams, governance bodies, and senior leaders. The role includes direct people leadership and accountability for developing an effective, collaborative, and scientifically excellent team.

Key Responsibilities

Scientific Strategy and Functional Leadership

• Develop and deliver the computational immunogenicity strategy in alignment with Development Sciences priorities and key scientific objectives.
• Serve as the discipline expert and primary contact for AI/ML-enabled immunogenicity, protein engineering, and translational modeling.
• Identify emerging scientific and technology trends, assess their relevance, and translate them into short- and long-term functional objectives.
• Create, champion, and implement innovative approaches that improve candidate selection, risk mitigation, and transition success.

AI/ML-Based Immunogenicity and Protein Modeling

• Lead development and deployment of predictive models for preclinical and clinical immunogenicity risk assessment.
• Integrate ADA incidence, PK/PD, HLA, sequence, structure, developability, assay, and patient-level data using machine learning and deep learning approaches.
• Apply protein language models, foundation models, transformers, generative AI, and physics-informed modeling to identify immunogenicity drivers, biomarkers, and design opportunities.
• Develop or guide methods to predict ADA incidence and persistence, T-cell epitope content, HLA-associated risk, patient susceptibility, and drug-like properties of biologics.

Systems Immunology, Multi-Omics, and Translational Modeling

• Integrate transcriptomic, proteomic, single-cell, spatial biology, flow cytometry, bioanalytical, and clinical datasets to characterize immune responses to biologics.
• Build computational frameworks linking in vitro and ex vivo assays, nonclinical observations, molecular mechanisms, and clinical ADA or neutralizing-antibody outcomes.
• Identify biomarkers associated with immune activation, tolerance, and ADA development, and use findings to inform translational and clinical strategies.

Generative AI, Knowledge Integration, and Data Platforms

• Lead development of PLM- and LLM-enabled tools for scientific knowledge mining, hypothesis generation, and immunogenicity risk assessment.
• Guide retrieval-augmented generation and agentic workflows that use scientific literature, historical studies, internal reports, and regulatory guidance.
• Establish integrated, traceable immunogenicity data assets and scalable data pipelines spanning discovery, nonclinical, and clinical development.
• Ensure analytical approaches are reproducible, scientifically defensible, appropriately documented, and fit for their intended use.

Cross-Functional Influence and Communication

• Collaborate with experts across Discovery, Protein Sciences, Bioanalysis, Clinical, Regulatory, Toxicology, Data Science, and other Development Sciences functions.
• Communicate complex scientific concepts, model performance, limitations, and recommendations clearly to technical and non-technical audiences.
• Present scientific strategies and results to project teams, functional leadership, governance committees, senior management, and internal or external partners.
• Build strong working relationships, reconcile differing technical perspectives, and influence decisions through evidence-based recommendations.

People Leadership and Talent Development

• Manage, mentor, and develop a team of computational scientists and/or computational protein engineers; set clear priorities and maintain accountability for high-quality delivery.
• Provide technical guidance, performance coaching, career development, and timely feedback to direct reports.
• Create an inclusive, collaborative environment that encourages scientific rigor, innovation, knowledge sharing, and continuous learning.
• Assess capability needs and help build the talent, partnerships, and operating model required to achieve functional goals.

Qualifications

Required Qualifications

• Ph.D. in computational biology, computational structural biology, bioinformatics, biomedical informatics, computer science, data science, biophysics, or a related scientific field, with typically 8 or more years of related work experience; or a Master’s degree with typically 14 or more years.
• Demonstrated discipline expertise in computational protein science, biologics discovery or development, AI/ML, and predictive modeling.
• Proven ability to define scientific strategy, lead complex multidisciplinary programs, and deliver innovative computational capabilities with measurable scientific or product impact.
• Demonstrated people-management experience, including leading scientific teams, setting priorities, coaching employees, and supporting performance and career development.
• Exceptional written, verbal, and presentation skills, with the ability to communicate clearly and persuasively to scientific, non-scientific, and senior-leadership audiences.
• Strong record of collaboration and influence across diverse internal and external groups.
• Experience with HLA binding prediction, T-cell epitope prediction, MHC-II modeling, single-cell analysis, knowledge graphs, causal AI, RAG systems, or biomedical language models.
• Experience handling, curating, integrating, and governing large experimental, biological, clinical, structural, or multi-omics datasets.
• Experience developing and maintaining reproducible data pipelines, automated workflows, and deployable computational tools.
• Demonstrated understanding of physical principles governing protein structure, folding, binding, developability, and molecular recognition.

Scientific and Technical Expertise

• Protein language models, generative protein design, structural modeling, and computational antibody engineering.
• Biologics developability, property prediction, sequence and structure optimization, and translational decision support.
• Immunology, adaptive immune responses, ADA and neutralizing-antibody biology, immune tolerance, and translational medicine.
• Proficiency in Python and relevant scientific computing, data science, and machine-learning frameworks such as PyTorch, TensorFlow, scikit-learn, or XGBoost.
• Cloud or scalable computing environments such as AWS, Azure, Databricks, or Snowflake, and effective scientific data visualization.

Preferred Qualifications

• Experience with immunogenicity risk assessment, ADA data interpretation, and relevant FDA or EMA guidance.
• Experience converting computational prototypes into tools that are adopted by research or development teams.
• Publication, patent, invited-presentation, or other record demonstrating scientific innovation and external or internal recognition.
• Experience building collaborations across computational, experimental, translational, and clinical disciplines.

Critical Success Factors

• Strategic scientific leadership paired with hands-on technical depth.
• Innovation that produces practical, trusted, and scalable solutions for biologics development.
• Clear, concise, and influential communication across levels and disciplines.

…