Materialwissenschaftler/in (Computational Materials Scientist) für Simulation und KI-gestützte Materialforschung

Description du poste

We’re hiring a Computational Materials Scientist with a strong background in both physics-based simulation and machine learning-driven scientific modeling to build and scale domain-specific simulation and data generation workflows. You’ll work with ML researchers and experimental teams to ensure high-quality data for model training and evaluation. This role is critical to our ability to generate high-fidelity scientific data, validate predictive models, and bridge computational insights with experimental outcomes. Key Responsibilities: Advanced Simulation Development & Scientific Computing - Design, develop, and scale high-throughput computational materials workflows utilizing Density Functional Theory (DFT), Molecular Dynamics (MD), phase-field modeling, and related first-principles simulation methods, including their application to solid-state synthesis processes and phase transformations. - Architect and optimize computational pipelines capable of generating and managing large-scale materials datasets comprising tens of thousands of compounds, structures, and simulation outputs. - Develop novel simulation strategies and workflow automation tools to improve throughput, reproducibility, and scientific rigor. Scientific Data Generation & Validation - Generate high-quality computational datasets for AI/ML model training, validation, and benchmarking across diverse materials systems. - Establish rigorous validation frameworks to benchmark simulation outputs against experimental measurements and published scientific literature. - Evaluate uncertainty, accuracy, and predictive performance of computational methodologies across multiple materials domains. Cross-Functional Research Leadership - Partner closely with experimental scientists, materials engineers, and machine learning researchers to align computational predictions with real-world material behavior. - Translate experimental observations into simulation hypotheses and computational models that accelerate research and product development. - Translate experimental and physical insights into data-driven and machine learning-based models for materials discovery and optimization. - Provide scientific leadership on computational methodologies, simulation best practices, and data quality standards across research programs. Innovation & Technical Excellence - Drive continuous improvements in data quality, coverage, reproducibility, and scalability of scientific workflows. - Contribute to the development of next-generation computational frameworks that integrate physics-based simulation with AI-driven materials discovery. - Stay at the forefront of advances in computational materials science, high-performance computing, and scientific machine learning. Qualifications: - PhD in Materials Science, Physics, Chemistry, Chemical Engineering, Computational Science, or a closely related quantitative discipline (candidates near completion of the PhD may also be considered). - Strong academic background from a top-tier university in core materials science and physics, including quantum mechanics, thermodynamics, and solid-state physics. - Extensive experience developing and deploying advanced computational materials science workflows using DFT, MD, or equivalent atomistic and mesoscale simulation techniques, including applications to solid-state synthesis, thermodynamic analysis, and phase transformations. - Demonstrated expertise in high-throughput simulation of large materials libraries, including datasets containing 10,000+ materials, structures, or computational experiments combined with machine-learning-based force fields or related hybrid modeling approaches - Proven track record of validating computational predictions against experimental data and translating simulation results into actionable scientific insights. - Proven ability to integrate physics-based modeling with data-driven or machine learning approaches, including experience in synthetic data generation or advanced AI methods applied to scientific workflows. - Demonstrated combination of deep materials science expertise with formal academic training or graduate-level coursework in machine learning, computer science, or related quantitative fields. - Experience working with large-scale scientific datasets and computational workflows. - Strong experience working in interdisciplinary environments involving experimental researchers, computational scientists, and machine learning teams. - Proficiency with scientific computing, programming skills (Python required), workflow orchestration, high-performance computing environments, and large-scale data analysis. - Excellent written and verbal communication skills in English. Preferred: - Exposure to state of the art machine learning, including reinforcement learning or large language models Why Join Us: - Work alongside world-class researchers and engineers tackling frontier challenges in materials discovery and scientific AI. - Lead mission-critical computational research that directly influences breakthrough technologies and products. - Access cutting-edge computational infrastructure and collaborative multidisciplinary research environments. - Competitive compensation, comprehensive benefits, and flexible working arrangements. - Opportunity to make a visible and lasting impact on the future of materials innovation