Materials Informatics Scientist (Evaluation-focused)

Skip to main contentEnglishEnglishBack to all jobsMaterials Informatics Scientist (Evaluation-focused)BerlinFull-timePermanent employeeApply for this jobYour missionDefine how AI models for materials discovery are evaluated, compared, and trusted Dunia is building AI for one of the hardest unsolved problems in science: turning materials discovery from an academic, trial-and-error process into a programmable, scalable discipline. As our models grow more complex and our experimental throughput increases, the limiting factor is no longer generating predictions, but knowing which ones to believe. As Materials Informatics Scientist (Evaluation-focused), you will own the evaluation and validation of AI models applied to materials discovery. Your role is to ensure that model performance claims are meaningful, comparable, and decision-relevant, and that progress in AI for Materials reflects real improvements in discovery, not artifacts of metrics or datasets. This role is not about building new models. It is about defining the standards by which models are judged. Your tasks will include: Own evaluation as a scientific discipline Design, implement, and maintain evaluation frameworks for AI models across materials discovery tasksDefine metrics and protocols that reflect generalization, robustness, uncertainty, and experimental relevanceIdentify failure modes, dataset leakage, and misleading performance signalsInterrogate and compare models Systematically benchmark different model classes, training regimes, and representationsEvaluate tradeoffs between accuracy, uncertainty, data efficiency, and usabilityProvide clear, defensible recommendations on which models to trust, deploy, or retireConnect AI performance to real outcomes Link model behavior to experimental results and program-level objectivesDistinguish improvements that change decisions from those that only improve abstract scoresHelp research and programs teams understand what current models can and cannot reliably doBuild robust analytical tooling Develop and maintain professional-grade scripts and analysis pipelines for evaluation and benchmarkingVisualize complex, high-dimensional results in ways that surface real insightEnsure disciplined, reproducible handling of data, code, and resultsCommunicate truth clearly Present findings clearly to AI researchers, materials scientists, and leadershipProduce concise summaries that align the organization around a shared view of evidence and uncertaintyAct as an independent scientific reference point when claims require validationYour profilePhD (strongly preferred) or Master’sdegree in materials science, chemistry, physics, machine learning, or a related fieldSignificant experience (typically 5–8 years) working with scientific or ML systems under real-world uncertaintyDemonstrated experience evaluating, benchmarking, orvalidatingmodels rather than only building themStrong programming skills in Python and scientific data toolingDeep appreciation for rigor, reproducibility, and careful interpretation of resultsEnglish fluency, additional languages preferredAbout usDunia, meaning “world” in over 20 languages, reflects our focus on building technologies that deliver abundance globally. By combining physics, AI, and automation, we accelerate materials discovery for next-generation energy and industrial systems. Our work helps make energy more accessible and materials more affordable and resilient while reshaping how science moves from idea to impact. Join us to work on problems where progress truly compounds.Need more convincing? -->  Watch this videoWe strive to create a diverse and inclusive workplace where everyone feels welcome and safe to be their authentic self. Non-traditional career paths are welcome and valued. If you share our vision, you can be certain that we want you to succeed. You might be just the right candidate for this or for other roles that have not opened yet. Reach out, and follow us on LinkedIn!Apply for this job