Overview
Define 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
Full job description
Your Mission
Define 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 tasks
- Define metrics and protocols that reflect generalization, robustness, uncertainty, and experimental relevance
- Identify failure modes, dataset leakage, and misleading performance signals
Interrogate and compare models
- Systematically benchmark different model classes, training regimes, and representations
- Evaluate tradeoffs between accuracy, uncertainty, data efficiency, and usability
- Provide clear, defensible recommendations on which models to trust, deploy, or retire
Connect AI performance to real outcomes
- Link model behavior to experimental results and program-level objectives
- Distinguish improvements that change decisions from those that only improve abstract scores
- Help research and programs teams understand what current models can and cannot reliably do
Build robust analytical tooling
- Develop and maintain professional-grade scripts and analysis pipelines for evaluation and benchmarking
- Visualize complex, high-dimensional results in ways that surface real insight
- Ensure disciplined, reproducible handling of data, code, and results
Communicate truth clearly
- Present findings clearly to AI researchers, materials scientists, and leadership
- Produce concise summaries that align the organization around a shared view of evidence and uncertainty
- Act as an independent scientific reference point when claims require validation
Qualifications And Requirements
- PhD (strongly preferred) or Master’sdegree in materials science, chemistry, physics, machine learning, or a related field
- Significant experience (typically 5–8 years) working with scientific or ML systems under real-world uncertainty
- Demonstrated experience evaluating, benchmarking, orvalidatingmodels rather than only building them
- Strong programming skills in Python and scientific data tooling
- Deep appreciation for rigor, reproducibility, and careful interpretation of results
- English fluency, additional languages preferred
Requirements & qualifications
- PhD (strongly preferred) or Master’sdegree in materials science, chemistry, physics, machine learning, or a related field
- Significant experience (typically 5–8 years) working with scientific or ML systems under real-world uncertainty
- Demonstrated experience evaluating, benchmarking, orvalidatingmodels rather than only building them
- Strong programming skills in Python and scientific data tooling
- Deep appreciation for rigor, reproducibility, and careful interpretation of results
- English fluency, additional languages preferred
Tips for this job
Practical Job and Scholarship guidance. These tips do not replace official rules or create new eligibility requirements.
- Tailor the CV and application to the responsibilities and required skills stated on the official employer page.
- Use concrete evidence of relevant work, projects and measurable results rather than generic claims.
- Confirm location, work authorization, remote restrictions and sponsorship terms before applying.
- Apply through the original employer or official recruitment destination shown on this page.
Verification notes
Discovered directly from the employer’s published Personio open-positions XML feed. All public jobDescriptions sections were normalized into complete candidate-facing content.
Job and Scholarship is the discovery and verification layer. Confirm eligibility, dates, salary/funding and application instructions on the original source before submitting anything.
Dunia Careers ↗Browse current Job and Scholarship listings from Dunia Careers →
