Research Scientist – Machine Learning

at  Svante

REQUIRED SKILLS AND QUALIFICATIONS:

• You have MSc/PhD in Materials Science, Chemistry, Chemical Engineering, or a related field with a focus on computational materials science, machine learning, or a closely related area.
• You have demonstrated expertise in machine learning techniques, particularly Bayesian optimization, and their application to materials design and discovery.
• You have strong programming skills in languages such as Python, MATLAB, or R, and experience in machine learning libraries such as scikit-learn, TensorFlow, or PyTorch.
• You have experience with MOF synthesis, characterization, and data analysis techniques, with a particular emphasis on PXRD patterns.
• You have experience in materials discovery and screening.
• You have track record of publication in peer-reviewed journals and presentation at scientific conferences.

BONUS SKILLS AND QUALIFICATIONS:

• You have familiarity with molecular features in MOFs, including ligand design, metal coordination environments, pore size, and surface chemistry.
• You have familiarity with crystal structure prediction methods using machine learning techniques, such as graph neural networks, convolutional neural networks, or other advanced machine learning algorithms.
• You have advanced skills in other computational techniques such as DFT and MD.

PURPOSE OF THE ROLE:

We are seeking a motivated and qualified Research Scientist with a background in the development and application of Machine learning (ML) techniques in material science at R&D Centre of Excellence of Svante. You will have expertise in large language models, ML-based materials property prediction, and a strong familiarity with metal-organic frameworks (MOFs) and their characterization techniques.

WHAT SUCCESS LOOKS LIKE IN THIS ROLE:

• You will conduct research to develop and apply large language models and machine learning algorithms specifically tailored for the design, synthesis, and characterization of MOFs.
• You will collaborate closely with the sorbent development team to design and screening of new sorbents optimized for CO2 capture, leveraging computational chemistry & machine learning methodologies.
• You will apply ML-based optimization techniques (including Bayesian optimization) to optimize experimental conditions for MOF synthesis and performance.
• You will develop and implement machine learning models for predicting key material properties of MOFs, such as gas adsorption capacity, selectivity, and stability.
• You will collaborate closely with experimentalists to design and interpret experiments, validate computational predictions, and guide experimental synthesis efforts.