Senior Materials Scientist - AI/ML for Materials Design

Avery Dennison•Mentor, OH

13d

About The Position

We are seeking an exceptional scientist to help pioneer AI-enabled materials discovery and optimization across complex polymeric and soft materials systems. This role sits within the Materials Science & Characterization (MSC) group and will drive the integration of machine learning, physics-based modeling, and experimental design to accelerate innovation across Avery Dennison’s global product portfolio. The role requires intellectually curious scientists who are excited by hard interdisciplinary problems and who enjoy bringing together fundamental physics, data science with highly practical impact. Lead the development of predictive AI-enabled materials discovery frameworks that connect process → structure → properties → performance across multiple spatial and temporal scales. The successful candidate will work at the frontier of materials science, physics-informed AI, and autonomous experimentation, developing predictive and generative models capable of accelerating innovation across Avery Dennison’s global materials portfolio. We are particularly interested in scientists excited about building and applying new computational frameworks that integrate machine learning, simulation, and experimentation for complex real-world industrial materials systems.

Requirements

Ph.D. in Materials Science, Chemical Engineering, Polymer Science and Engineering, Mechanical Engineering, Physics or a related discipline.
3–5 years of post-PhD experience (industrial and/or postdoctoral) applying AI/ML to physical systems or materials problems supported by a strong publication record.
Strong foundation in materials physics, soft matter, polymers, or complex materials systems.
Demonstrated expertise in machine learning frameworks such as PyTorch, TensorFlow, JAX, or similar tools and commonly used ML/deep learning libraries and materials informatics, active learning and Bayesian optimization.
Advanced programming skills in Python and scientific computing environments including the use of mathematical packages (Matlab, Mathematica, R etc…) in both Windows and Linux environments.
Experience in developing large language model (GenAI) agents, domain specific prompt engineering and different RAG architectures to wrap around scientific databases.
Proven track record to think critically and solve problems using the above mentioned fields and techniques. Be comfortable in spanning theory, experiments and production environments
Good organizational and planning skills; ability to balance multiple tasks and projects simultaneously.
Ability to work independently as well as in a diverse multi-functional team and ability to interact effectively with both internal and external customers.
Less than 10% travel expected

Responsibilities

Develop and deploy machine learning and deep learning models to accelerate materials design and formulation optimization.
Implement physics-informed ML and hybrid modeling frameworks combining thermodynamics, kinetics, rheology, and materials physics with modern AI architectures.
Apply inverse design approaches to identify materials formulations and structures that achieve targeted performance.
Integrate molecular, mesoscale, and continuum modeling approaches with AI-driven surrogate models.
Utilize techniques such as Molecular Dynamics (MD), Dissipative Particle Dynamics (DPD), Mean-field and coarse-grained models (CGMD), Finite element and continuum modeling (FEA) to inform ML Modeling strategies.
Develop multi-fidelity modeling strategies combining simulations, experimental data, and literature sources.
Design and curate model-ready materials datasets integrating experimental, simulation, and manufacturing data.
Develop scalable pipelines for data ingestion, feature engineering, and model validation.
Implement frameworks for active learning and data-efficient modeling.
Collaborate with experimental teams to guide high-value experiments using predictive models.
Develop approaches for AI-guided experimental design and closed-loop optimization.
Contribute to the development of autonomous or self-driving materials laboratories.
Work closely with subject matter experts including computational scientists, polymer chemists, formulation scientists, process engineers, and analytical experts.
Translate complex models into actionable insights for product and process development.
Communicate technical findings through reports, publications, and internal presentations.