CAREERS
Work at Thetic
Help connect scientific knowledge, machine learning, and experimental evidence to discover materials with useful, measurable properties.
We welcome people who combine technical depth, careful judgment, and a drive to solve difficult problems. Our work spans computational discovery, scientific data, predictive modeling, and experimental validation.
Areas of focus
Materials Scientist
Computational discovery & experimental validation
Connect materials knowledge, computational predictions, and experimental evidence to guide the search for materials with useful properties.
The work
- Translate application requirements into measurable material properties and research objectives.
- Evaluate scientific literature, datasets, and predicted candidates for physical plausibility and practical relevance.
- Develop computational screening approaches and help prioritize candidates for further investigation.
- Define validation plans with experimental partners and interpret results, including unsuccessful outcomes.
- Work with machine learning engineers to improve how scientific evidence informs subsequent predictions.
Relevant experience
- A background in materials science, chemistry, physics, or a closely related field.
- Experience with computational materials methods and an understanding of experimental characterization.
- Scientific programming and data analysis skills.
- Sound judgment about uncertainty, reproducibility, synthesis feasibility, and real-world constraints.
Machine Learning Engineer
Scientific data & discovery systems
Develop the models, data pipelines, and software that connect scientific knowledge to candidate predictions and experimental feedback.
The work
- Turn scientific literature, structured datasets, and experimental results into reliable, traceable data.
- Integrate, train, and evaluate models for predicting material properties and prioritizing candidates.
- Build reproducible workflows that connect data processing, model execution, and scientific evaluation.
- Capture experimental outcomes so they can inform model evaluation and future training.
- Work with materials scientists to measure performance against meaningful scientific objectives.
Relevant experience
- Strong Python and software engineering skills.
- Experience applying machine learning to complex scientific or technical data.
- Practical experience with data pipelines, model evaluation, and reproducible experiments.
- The ability to build reliable systems while reasoning carefully about data quality, uncertainty, and model limitations.
