Materials Science AI Engineer

Job Title: Materials Science AI Engineer

Job Summary

We are seeking a Materials Science AI Engineer to design, develop, and deploy machine learning and AI solutions that accelerate materials discovery, characterization, and optimization. This role sits at the intersection of materials science, data science, and artificial intelligence, translating physical insights into scalable computational models that drive innovation across materials R&D.

Key Responsibilities

• Develop and implement machine learning models for materials property prediction, structure–property relationships, and performance optimization
• Integrate domain knowledge from materials science, chemistry, or physics into AI/ML workflows
• Process, curate, and analyze experimental and simulation datasets (e.g., spectroscopy, microscopy, DFT, molecular dynamics)
• Collaborate with materials scientists and experimental teams to guide model development and validation
• Design data pipelines for materials data ingestion, cleaning, feature engineering, and model deployment
• Apply techniques such as deep learning, graph neural networks, Bayesian optimization, and generative models to materials problems
• Evaluate model performance and uncertainty; ensure interpretability and physical plausibility of predictions
• Deploy AI models into research or production environments and maintain model lifecycle
• Stay current with advances in materials informatics, AI methodologies, and computational tools

Required Qualifications

• Master’s or PhD in Materials Science, Chemistry, Physics, Computer Science, or a related field
• Strong foundation in materials science concepts (e.g., crystallography, thermodynamics, phase diagrams, structure–property relationships)
• Hands-on experience with machine learning and data science techniques
• Proficiency in Python and ML frameworks (e.g., PyTorch, TensorFlow, scikit-learn)
• Experience working with scientific data and numerical methods
• Ability to communicate complex technical ideas across interdisciplinary teams

Preferred Qualifications

• Experience with materials databases (e.g., Materials Project, OQMD, AFLOW)
• Familiarity with computational materials tools (e.g., DFT, MD, LAMMPS, VASP)
• Experience with graph-based models, physics-informed ML, or active learning
• Knowledge of cloud computing, MLOps, or high-performance computing (HPC)
• Publication or patent record in materials informatics or related fields