Associate Principal Scientist, Biologics AI

About the Company

Responsibilities

• ● Strategic leadership and vision : Define and drive the AI strategy for biologics discovery and engineering, setting priorities and roadmaps that integrate AI and wet lab capabilities and deliver measurable impact on pipeline goals.
• ● Program ownership : Lead multiple cross functional discovery initiatives from problem framing through deployment, ensuring rapid translation of computational insights into experimental design and decision making.
• ● Advanced ML innovation : Architect, develop, and guide application of cutting edge models-protein language models, structure informed and geometric methods, de novo/protein design, and multi modal learning that fuses sequence, structure, and biological activity data-to solve high value scientific problems.
• ● AI-wet lab integration at scale : Establish closed loop design-build-test-learn workflows with experimental teams, formalizing feedback cycles, uncertainty quantification, and active learning to improve model reliability and throughput.
• ● Data strategy and governance : Set standards for high quality data generation, curation, and metadata; partner with wet lab leaders to design assays and campaigns that maximize ML utility and reproducibility; influence data platform evolution in collaboration with informatics and engineering.
• ● End to end ML lifecycle leadership : Oversee and improve processes across data pipelines, model development, validation, deployment, monitoring, and continuous improvement, including best practices for reproducibility, documentation, and scientific rigor.
• ● Technical mentorship and team development : Mentor and upskill scientists across AI/ML and experimental domains; provide day to day technical guidance and contribute to recruitment and development of a high performing team.
• ● Stakeholder influence and communication : Communicate strategy, progress, risk, and scientific insights to senior stakeholders; influence portfolio decisions and advocate for AI enabled approaches internally and with external partners.
• ● External scientific leadership : Drive publications, patents, and external visibility; represent AstraZeneca in collaborations and at scientific venues; evaluate and integrate emerging methods and tools. Required Qualifications
• ● Domain impact in biologics AI : Demonstrated track record applying AI/ML to proteins, antibodies, or related biologics, with clear examples of methods translated into experimental outcomes, platform capabilities, or pipeline decisions.
• ● Deep technical expertise : Hands on leadership in developing and deploying advanced ML (deep learning, generative models, structure aware and geometric methods, sequence/structure multi modal models) for protein sequence modeling, structure informed prediction, de novo design, or biologics optimization.
• ● Closed loop integration : Proven success establishing iterative computational-experimental cycles (e.g., active learning, design-build-test-learn), including designing experiments to interrogate model predictions and improve data/model quality.
• ● Lifecycle and systems : Experience leading the full ML lifecycle at scale-data design and preprocessing, model architecture, training/evaluation, deployment, monitoring, and maintenance-using modern ML frameworks (e.g., PyTorch, TensorFlow) and software engineering best practices.
• ● Data and platforms : Experience with cloud based ML environments and scalable data workflows; ability to specify requirements and partner with data engineering/IT to evolve production ML systems that support discovery at scale.
• ● Cross functional leadership : Strong record of influencing and delivering in matrixed, multidisciplinary environments, bridging AI scientists, computational biologists, protein engineers, and wet lab teams across sites.
• ● Scientific communication : Excellent communication skills with the ability to synthesize complex technical concepts for diverse audiences and to shape scientific and portfolio decisions.
• ● Innovation and delivery : Evidence of scientific innovation and impact through publications, patents, platform creation, or deployment of AI methods that materially improved experimental or business outcomes. Preferred Qualifications
• ● Protein and antibody engineering : Experience with antibody/nanobody/protein engineering, including de novo design and multi objective optimization for developability, stability, and functional performance.
• ● Advanced methodologies : Expertise with generative models (e.g., diffusion, autoregressive LMs), geometric deep learning/graph neural networks, Bayesian optimization, uncertainty quantification, and active learning for guided experimentation.