Hiring nowChemistry, materials and process discovery

Materials Informatics Scientist

Also called Materials ML Scientist

A Materials Informatics Scientist predicts material properties and decides which candidates are worth making. They cut the number of lab experiments needed to find a material that works, which saves time and focuses scarce lab capacity.

What they do

Builds models that link a material's composition and structure to the properties the company cares about. Pulls together data from materials databases, simulation runs and lab measurements, and cleans it. Chooses how to represent a material so a model can learn from it. Screens large candidate spaces, ranks them, and says how uncertain each prediction is. Works with chemists and lab teams to pick the next batch of experiments, then feeds the results back into the models. Writes down where the models fail and what data would fix that.

What a strong hire delivers

A working screening pipeline that takes a target property and returns a ranked shortlist of candidates. Each candidate comes with an uncertainty estimate and a plan for how to validate it in the lab. A clear record of how well past predictions held up against measurements. Agreed priorities with the lab team, so experiments follow the model's best guesses and the data gaps that matter most.

How you can tell they are good

Ask them to walk through a screening project from raw data to a material that was actually made and tested. Listen for how they chose the representation, how they judged uncertainty, and what happened when predictions missed. Strong people talk about prospective results, not just cross-validation scores. Ask what they would not trust their model to do.

Why it is hard to fill

The title varies widely. People are called materials informatics scientists, computational chemists, ML scientists or simulation engineers. Few have both real domain depth and modern machine learning practice. Most lean one way. Chemists may lack modelling rigour, and ML engineers often misjudge what the data can support. Candidates who have seen predictions validated in a lab are rarer still.

Where to find them

Look in computational materials science and chemistry groups, chemical engineering research teams, and scientific ML labs. Strong candidates also come from battery, polymer, catalyst and semiconductor companies with in-house modelling teams, and from startups built around materials discovery. Postdoctoral researchers who moved from simulation into data-driven screening are a common source. Industrial R&D groups are another.

Indicative pay

Not enough published evidence yet to give a fair range for this role, which is common for work this new. We benchmark it for you as part of a search.

Interview questions for a Materials Informatics Scientist

  1. Tell us about a screening project where your predictions were tested in the lab. What held up and what did not?

    A strong answer names the property, the candidates chosen, and the measured outcome, including misses. It explains what they changed afterwards. Worry if they only cite retrospective test scores or cannot say what was actually synthesised.

  2. How do you choose a representation for a material when data is scarce?

    Good answers compare options such as composition features, structural descriptors and learned embeddings, and tie the choice to data size and the property. They mention physical constraints and baselines. Worry about defaulting to a deep model every time.

4 more questions, with what a strong answer covers, are in the Role Kit.

Job description you can post

We are hiring a Materials Informatics Scientist to help us decide which materials are worth making. You will build models that predict properties, rank candidates and tell us how sure we are. You will work closely with our chemists and lab team to turn predictions into tested results.

What you will do

  • Build and maintain models that predict material properties from composition and structure
  • Assemble and clean data from databases, simulations and lab measurements
  • Screen candidate spaces and produce ranked shortlists with uncertainty estimates
  • Write validation plans for each recommended candidate
  • Work with lab teams to select experiments and feed results back into the models
  • Track prospective accuracy and report where models fail
  • Document methods so others can reproduce and extend them

What you will bring

  • Demonstrated work taking a materials or chemistry prediction through to lab validation
  • Experience choosing and comparing material representations for learning
  • Practical command of uncertainty estimation and model calibration
  • Fluency in scientific computing and in working with simulation outputs
  • Experience designing experiments or selecting samples under a limited budget
  • Clear communication with experimental scientists

Nice to have

  • Experience with molecular simulation workflows
  • Background in optimisation or active learning methods
  • Work in batteries, polymers, catalysts or semiconductors

Free to use and adapt. If it saves you time, a link back to this page is appreciated.

Skills that matter

  • Scientific domain expertiseAdvancedApply disciplinary theory and experimental standards
  • Deep learningAdvancedBuild and diagnose trainable neural models
  • Experimental designWorkingChoose comparisons that identify credible effects
  • Optimisation and operations researchWorkingChoose actions subject to objectives and constraints

Other roles in chemistry, materials and process discovery

Hiring nowAI Computational ChemistAn AI Computational Chemist builds and validates learned models that stand in for expensive chemical calculations. The work lets a company explore…Hiring nowAI Process Optimisation EngineerAn AI Process Optimisation Engineer builds models of chemical or industrial processes and uses them to raise yield and efficiency without breaching…EmergingAutonomous Materials Discovery ScientistAn Autonomous Materials Discovery Scientist links model-driven candidate selection to laboratory testing in a closed loop. They help a company find…

Related roles in other families

Hiring nowScientific Machine Learning ScientistScientific machine learning and research computingA Scientific Machine Learning Scientist builds learned models that obey the physics, chemistry or biology of a problem. They matter because a model…Hiring nowAI Research Software EngineerScientific machine learning and research computingAn AI Research Software Engineer turns scientific machine learning ideas into software that other people can run, trust and extend. They give a…EmergingAI Scientific Workflow EngineerScientific machine learning and research computingAn AI Scientific Workflow Engineer connects data, models and instruments into reproducible science pipelines. They make sure results can be traced…EmergingAI Reproducibility SpecialistScientific machine learning and research computingAn AI Reproducibility Specialist independently reruns AI-supported scientific claims and reports what holds and what does not. They protect the…

How we wrote this

Role definitions are our own editorial work, checked against occupational classifications, standards, research and employer pages. Titles vary by company, and this is a description of the work, not a job advert.

← Chemistry, materials and process discoveryAll new job families

Start a search

Hiring a Materials Informatics Scientist?

Tell us the work. We find the people already doing it, whatever their job title says, and you meet them already interviewed for your role.