Associate Principal Scientist – Biologics AI Innovation

AstraZeneca•Waltham, MA

3d•Onsite

About The Position

We are seeking an experienced and visionary Associate Principal Scientist to drive Biologics AI innovation at AstraZeneca’s US R&D centers in Waltham, MA or Gaithersburg, MD. This is a pivotal scientific leadership role focused on integrating state-of-the-art artificial intelligence with wet-lab discovery to accelerate biologics engineering and enable the design of next-generation biotherapeutics. You will work collaboratively across computational and experimental functions, help shape the direction of AI-enabled research, and champion the generation, curation, and translation of high-quality data to power biologics discovery.

Requirements

PhD in computer science, machine learning, bioinformatics, computational biology, physics, chemistry, mathematics, engineering, or a related quantitative discipline, with typically 5+ years of relevant experience in academia and/or industry; alternatively, a Master’s degree with 8+ years of relevant experience.
Proven experience applying AI/ML to biological or molecular design problems, with strong relevance to proteins, antibodies, biologics, or related therapeutic modalities.
Demonstrated hands-on expertise in developing and deploying deep learning and other machine learning models for one or more of the following: protein sequence modeling, structure-informed modeling, generative modeling, molecular/property prediction, de novo design, or biologics optimization.
Experience working across the full machine learning lifecycle, including data preprocessing, dataset design, model architecture development, model training, evaluation, deployment, and productionization.
Demonstrated success in integrating computational modeling with experimental workflows, including close collaboration with wet-lab scientists and the use of experimental feedback to refine models and data strategy.
Strong programming skills in Python, along with experience in modern machine learning frameworks such as PyTorch, TensorFlow, or similar platforms.
Experience with cloud-based ML environments, scalable data workflows, and/or production ML systems in an academic or industry setting.
Strong scientific communication and collaboration skills, with a record of influencing cross-functional teams and contributing in matrixed, multidisciplinary environments.
Track record of scientific innovation and delivery, evidenced by a combination of publications, patents, impactful model development, or successful translation of AI methods into experimental or business outcomes.

Nice To Haves

Experience in antibody, nanobody, or protein engineering, including de novo design or optimization for developability and functional performance.
Experience with generative models, graph neural networks, Bayesian optimization, active learning, or other advanced approaches relevant to biologics discovery.
Familiarity with multi-modal learning approaches that combine sequence, structure, assay, and other biological data types.
Experience in scientific software deployment or productionalizing ML models to support discovery workflows at scale.
Experience establishing or improving data generation strategies in partnership with experimental teams to enhance downstream ML performance.
Prior experience mentoring scientists or leading projects in industrial or academic R&D environments.
Strong external scientific profile, including peer-reviewed publications, patents, invited talks, or conference presentations.

Responsibilities

Lead AI strategies for biologics discovery and engineering, with a strong emphasis on AI–wet-lab integration and rapid translation of computational insights into experimental design.
Drive the development and application of advanced machine learning models, including protein language models, structure prediction approaches, de novo protein design methods, and multi-modal models that integrate sequence, structure, and biological activity data.
Serve as a scientific leader and bridge across AI scientists, computational biologists, protein engineers, and wet-lab teams in the US, while partnering closely with global collaborators.
Guide the generation, curation, and effective use of high-quality wet-lab data, and provide feedback to experimental teams to improve data suitability for machine learning workflows.
Shape technical direction by evaluating and implementing emerging methods and best practices in machine learning, data science, computational biology, and protein engineering.
Contribute to an end-to-end ML lifecycle, including problem definition, data preprocessing, data infrastructure, model development, validation, deployment, and iterative improvement in partnership with scientific stakeholders.
Mentor junior scientists and contribute scientific leadership within Biologics AI, fostering a collaborative, innovative, and high-performing team culture.
Communicate scientific progress, technical strategy, and key challenges to stakeholders across disciplines and seniority levels, supporting strategic decision-making.
Contribute to scientific publications, patents, and external scientific visibility, and represent AstraZeneca through internal and external collaborations, presentations, and partnerships.