Senior Director MMAI & Outcome Prediction – AI for Precision Health

Apply multimodal AI methodologies to transform clinical development strategies by improving patient identification, trial enrichment, responder prediction, and endpoint optimisation. Lead advanced reanalysis of clinical trial datasets to uncover responder subgroups,   identify   predictive and prognostic biomarkers, and refine patient selection strategies. Use advanced modelling approaches such as causal inference, treatment effect estimation, and dynamic outcome prediction to strengthen development decisions and maximise asset differentiation across the portfolio.

1. Reinforce Foundation Models   with   Clinical and Real-World Data

Partner closely with internal AI research teams to translate advances in foundation models into practical biomedical applications. Design reinforcement strategies that   leverage   AstraZeneca’s clinical trial datasets, real-world healthcare data, and multimodal biological signals to improve model generalisability and predictive power. Develop reusable multimodal representations that capture disease biology across datasets and therapeutic areas, enabling scalable predictive modelling capabilities across the organisation.

1. Integrate Clinical Trials and Real-World Evidence   into   Continuous Learning Systems

Establish predictive modelling frameworks that integrate clinical trial data with real-world evidence to extend insights beyond controlled trial environments. Develop continuous learning systems capable of incorporating longitudinal patient outcomes from electronic health records, claims data, and diagnostic platforms. Enable post-launch monitoring of treatment outcomes and reinforcement of predictive models through real-world evidence, creating feedback loops that strengthen both development and care pathway strategies.

1. Establish   Enterprise Standards for Multimodal AI Validation and Governance

Define and implement enterprise-wide scientific standards for the validation, deployment, and lifecycle management of multimodal AI models. Establish rigorous frameworks for reproducibility, cross-site generalisability, bias mitigation, model explainability, and regulatory-grade evidence generation. Ensure that predictive and diagnostic models meet the scientific, regulatory, and operational requirements necessary for deployment in clinical research and healthcare environments.

• Contribute to the development of AI for Transform Care team members,   providing   expert guidance on precision medicine strategies, companion diagnostics, and AI-embedded clinical decision tools.

• Build and sustain strong internal and external collaborations across Commercial, R&D, key markets, academic leaders, and patient communities to ensure prioritised needs are addressed with scientific excellence.

• Advanced degree ( Master’s   or PhD) in a relevant field such as Biomedical Engineering, Data Science, Computational Biology, Bioinformatics, Digital Health, or Artificial Intelligence.

• + 5 years proven experience leading or contributing to AI-enabled medical or biological projects, such as biomarker discovery, digital pathology, patient stratification, clinical decision support, or disease   modeling

• Recognized   expertise   in multimodal AI applied to Oncology and BioPharma, with   demonstrated   impact in outcome prediction, computational diagnostics, or precision medicine strategy.

• Deep hands-on mastery of advanced machine learning methodologies including:

• Multimodal representation learning integrating radiology, digital pathology, spatial and bulk omics, molecular diagnostics, digital biomarkers, clinical trials, and real-world data

• Survival modelling, dynamic time-to-event prediction, and competing risk frameworks

• Causal inference methodologies including propensity   modeling , marginal structural models, uplift modelling, and treatment effect heterogeneity analysis

• Construction and validation of synthetic and external control arms using real-world evidence

• Development and validation of prognostic and predictive biomarkers across development phases

• Advanced risk stratification, patient subtyping, clustering, and disease trajectory modelling

• Longitudinal modelling of disease evolution and treatment response

• Strong   expertise   in computational imaging, high-dimensional omics integration, and multimodal feature fusion architectures.

• Proven experience defining validation strategies aligned with regulatory-grade evidence standards, including reproducibility frameworks, cross-site generalisability, bias mitigation, robustness testing, and model lifecycle monitoring.

• In-depth understanding of regulatory and compliance frameworks governing AI in healthcare, including medical device pathways, AI governance, transparency requirements, and data privacy regulations.

• Ability to critically dissect external AI architectures, data provenance, validation   methodology , and scalability claims.

• Extensive experience working with large-scale, heterogeneous healthcare datasets including EHR, claims, imaging repositories, genomic platforms, molecular diagnostic datasets, and global clinical trial databases.

• Strong scientific grounding in Oncology biology and clinical development, with the ability to connect modelling outputs to therapeutic mechanisms and development strategy.

• Advanced understanding of clinical trial design, enrichment strategies, endpoint optimisation, and evidence package construction.

• Solid knowledge of Market Access principles, value-based healthcare frameworks, and payer evidence requirements.

• Familiarity with companion diagnostics development and precision medicine strategy integration.

• Working knowledge of compliance and legal frameworks relevant to AI-enabled diagnostic and predictive tools.

• Deep understanding of healthcare data ecosystems and enterprise platforms, including EMR, CTMS, EDC, imaging systems, molecular data systems, and real-world data infrastructures.

• Experience deploying AI models within real-world clinical workflows and complex enterprise environments.

• Strong grasp of scalable AI infrastructure, data architecture principles, and model deployment constraints.

• Demonstrated   track record   leading large-scale digital health or AI transformation programs with measurable clinical and economic impact.

• Shown ability to shape global strategy and drive adoption across complex, matrixed, multinational organisations.

• Experience building and sustaining high-value external partnerships across academia, technology, diagnostics, and data ecosystems.

• Ability to translate complex computational concepts into clear strategic implications for senior leadership, regulators, clinicians, and payers.

• Entrepreneurial mindset with experience   operating   in innovation-driven or start-up-like environments.

• High level   of integrity, scientific rigor, and credibility, with the ability to influence at executive level.

• Motivated by delivering scientifically robust digital innovation that materially improves patient outcomes and treatment experience.