AI Research Lead, AI for Oncology Clinical Development

About the Company

Responsibilities

• ● , partnering across hematology, cell therapy, antibody-drug conjugates, small molecules, and biologics. Based in Barcelona, you will collaborate with global teams to define the questions that matter most, build models that answer them, and translate those models into clinical and regulatory realities. What could you achieve if your models were deployed where decisions are made
• ● Accountabilities
• ● AI Strategy and Roadmap: Co-own and evolve the AI strategy for early and late-phase oncology clinical development, aligning investments to the highest-value opportunities and setting a clear path from research to adoption
• ● Technical Leadership: Serve as the principal technical lead within matrixed teams, delivering complex, high-stakes AI programs on time and to a standard that withstands scientific and regulatory scrutiny
• ● Method Innovation: Evaluate and develop cutting-edge AI methods across problem framing, data readiness, governance, algorithm development, validation, and deployment; select the right tool for the right question
• ● Clinical Partnership: Partner with clinical development, biometrics, regulatory, and study teams to embed novel AI solutions into study design, operational execution, portfolio strategy, and go/no-go decision-making
• ● Evidence and Validation: Design rigorous evaluation frameworks, benchmarking protocols, and calibration plans to ensure models are reliable, interpretable, and fit for purpose in real-world clinical contexts
• ● External Ecosystem: Build and maintain collaborations with leading academic groups, technology partners, and industry consortia to access novel capabilities and shape standards that matter to oncology development
• ● Scientific Leadership: Represent AstraZeneca at scientific conferences and standards bodies; author first- or last-author publications in leading ML and clinical AI journals to advance the field and our influence
• ● Team Development: Mentor and support peers, fostering a culture of curiosity, pragmatic engineering, fast prototyping, and learning in public
• ● Impact Progression: Deliver near-term wins by solving defined study and program needs; scale insights into reusable platforms and playbooks that raise the bar across the portfolio

Requirements

• ● PhD in a quantitative discipline such as computer science, bioinformatics, computational biology, mathematics, physics, biophysics, computational neuroscience, biostatistics
• ● years' work experience outside of PhD with measurable impact (e.g. models delivered, patents, SaMD filings, first-author publications, open-source projects, standards-body participation)
• ● Exceptional software development and coding skills, leveraging frontier coding agent frameworks; knowledge of computing hardware a plus
• ● Deep understanding of machine learning fundamentals, with domain expertise in one or more of the following
• ● Training and tuning foundation models.
• ● Bayesian inference
• ● Temporal modeling
• ● Multimodal integration and modeling
• ● Model calibration and domain adaptation
• ● Data-centric AI: acquiring, creating, and curating datasets for model training / post-training / benchmarking / evals
• ● Model and data evaluations and benchmarking
• ● Model interpretability
• ● Model post-training and alignment
• ● Deep expertise in cancer biology
• ● Strong proficiency in augmenting but not supplanting daily knowledge work with agentic tools
• ● Team-oriented mindset
• ● Ability to proactively and independently deliver high-quality contributions at pace
• ● Up-to-date with the latest AI research and tools, proactively trying out those of interest, and ability to discern hype from true added value
• ● Comfort with ambiguity and a mindset to learn in public, prototype early, and fail forward
• ● Why AstraZeneca