Principal Scientist, AI-Native Discovery (Large Molecules)

Johnson & Johnson•San Diego, PA

13d•Onsite

About The Position

Johnson & Johnson Innovative Medicine is seeking a Principal Scientist to join its In Silico Discovery (ISD), In Silico Biologics team. The position focuses on integrating advanced AI, agentic workflows, predictive modeling, and computational design into therapeutic discovery programs. The scientist will connect computational capabilities with biologics discovery needs, represent In Silico Discovery on cross-functional teams, and use AI-enabled approaches to inform scientific strategy, experimental plans, and biologic candidate design and optimization. The role involves building AI-native workflows that link hypothesis generation, computational design, experimental testing, and model refinement. The scientist will help integrate scientific judgment, machine intelligence, experimental data, and computational methods, while contributing to rigorous and responsible AI adoption. The position also includes evaluating emerging technologies and supporting the company’s external scientific presence through publications, conferences, and external collaborations. The role is based in Spring House, Pennsylvania (preferred), Cambridge, Massachusetts, or San Diego, California (La Jolla area). There is no remote option, and some travel may be required.

Requirements

PhD in a relevant scientific or technical discipline.
At least 4 years of relevant drug discovery experience, including experience contributing to cross-functional discovery teams.
Knowledge of biologics discovery, candidate optimization, and therapeutic development processes.
Strong scientific leadership, communication, and stakeholder management skills, including the ability to clearly communicate complex data, models, and scientific concepts to partners with diverse technical backgrounds.
Demonstrated expertise in AI, machine learning, agentic AI, structural modeling, computational biology, or computational approaches for antibody design and optimization.
Experience representing a computational function on cross-functional projects and integrating computational and experimental data to inform program strategy and scientific decisions.
Hands-on experience with large-scale scientific data curation, aggregation, manipulation, integration, mining, and analysis across structured and unstructured data sources.

Nice To Haves

Experience in therapeutic target analysis, structural biology, antibody-antigen interaction modeling, computational protein design, and scientific data visualization.
Experience with multimodal biological data, generative modeling, foundation models, AI agents, or iterative design-build-test-learn workflows.
Experience developing, scaling, or adopting computational platforms and workflows in partnership with technology development teams.
A strong publication record and demonstrated contributions to the discovery or advancement of preclinical or clinical candidates.
Experience collaborating with academic institutions, biotechnology companies, technology partners, or contract research organizations.
Experience evaluating emerging computational technologies or external scientific innovation opportunities.
Experience influencing multidisciplinary discovery teams spanning computational and experimental functions.

Responsibilities

Partner with teams across In Silico Discovery to connect biologics discovery programs with relevant computational capabilities and AI-enabled approaches.
Partner with Biologics Discovery and Therapeutic Area teams to apply AI-enabled computational design, analysis, and decision support in therapeutic discovery programs.
Represent In Silico Discovery on cross-functional project teams and use computational insights to support program strategy and decision-making.
Apply predictive modeling, machine learning, generative approaches, agentic AI, structural modeling, and computational biology to support experimental strategy and biologic candidate design and optimization.
Advance AI-native workflows connecting hypothesis generation, computational design, experimental testing, and model refinement.
Evaluate emerging technologies and contribute scientific recommendations to internal development, acquisition, partnering, licensing, or M&A opportunities.
Promote responsible and scientifically rigorous AI adoption and contribute to a culture of collaboration, experimentation, continuous learning, and knowledge sharing.
Maintain awareness of advances in AI, computational biology, structural modeling, and biologics design.
Contribute to Johnson & Johnson’s external scientific presence through peer-reviewed publications, conference participation, and collaboration with external organizations.
Integrate human expertise, AI models, computational design, experimental workflows, and high-quality data to improve scientific learning and decision-making.