EmergingDrug discovery and molecular design

Molecular Generative Modelling Scientist

Also called Generative Chemistry Scientist

A molecular generative modelling scientist builds models that propose new, chemically valid compounds under clear constraints. They give a drug discovery team better candidates to test, which saves lab time and points effort at the right chemistry.

What they do

They build and run generative models that propose small molecules or other compounds against a target. The constraints are written down first: potency, selectivity, synthesisability, properties and known liabilities. They filter outputs for chemical validity, check novelty against known compounds, and score candidates with structure predictors and molecular modelling. They sit with medicinal chemists and biologists to agree which designs are worth making. When assay results return, they feed the data back into the next round. They also document what the model got wrong, because that is often the most useful thing the team learns.

What a strong hire delivers

In the first months, a strong hire turns a vague design brief into a clear set of constraints the team agrees on. They produce a candidate library with a validity and screening report that chemists trust. They set up novelty checks and a simple way to compare model output with assay results. They also leave behind a repeatable loop between model, shortlist, lab and feedback.

How you can tell they are good

Ask them to walk through one generation project from brief to assay result. A strong candidate explains how they set constraints, what they threw away and why. They can show a screening report and say where it was misleading. They talk about experimental utility, not just model scores. Be wary of anyone who treats chemical validity as the finish line or cannot say what the lab did with their output.

Why it is hard to fill

Titles vary, and much of this work sits inside computational chemistry or ML research roles. Few people are strong in both generative methods and real medicinal chemistry. Many ML candidates have never seen assay noise. Many chemists have never trained a generative model. Candidates who have closed the loop with a wet lab are rare, and they are often not looking under this title.

Where to find them

Look in computational chemistry teams, structural biology groups and pharmacology groups that have moved into modelling. Machine learning researchers who have worked on molecules are another source. They sit in AI-first drug discovery companies, biotech teams with strong data science, and research groups at frontier labs working on science. Search by the work they have done, such as constrained generation or assay feedback loops, not by title.

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 Molecular Generative Modelling Scientist

  1. Describe a generative chemistry project you ran. What were the constraints, and how did they change as it went on?

    A strong answer names concrete constraints, such as properties, synthesisability or selectivity, and explains what changed after feedback. It shows judgement about trade-offs. Worry if constraints were vague or never revisited after the lab results.

  2. How do you check that generated molecules are valid and genuinely novel?

    Look for valid structure checks, reasonableness filters, and novelty comparison against known compounds and training data. A good answer admits that valid and novel does not mean useful. Worry if they rely on one metric.

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

Job description you can post

We use AI to find better drug candidates faster. We are hiring a molecular generative modelling scientist to design models that propose chemically valid compounds under clear constraints, and to work closely with our chemists and biologists so the best ideas reach the lab.

What you will do

  • Build and run generative models for small molecule design against defined targets
  • Agree design constraints with chemists and biologists
  • Filter and score candidates for validity, novelty and likely activity
  • Produce candidate libraries with clear screening reports
  • Use assay results to improve each round of designs
  • Help choose which candidates go to the lab
  • Document model failures and what we learned

What you will bring

  • Shown work in molecular generation or constrained optimisation
  • Experience with molecular modelling and structure predictors
  • Evidence of working with experimental assay data
  • Ability to explain model results to medicinal chemists
  • Sound experimental design and sceptical habits
  • Clear written reporting of methods and limits

Nice to have

  • Experience with lab automation
  • Understanding of biosafety practice
  • Background in structural biology or pharmacology

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

Skills that matter

  • Biomolecular modellingAdvancedRepresent and predict molecular structure and interactions
  • Scientific domain expertiseAdvancedApply disciplinary theory and experimental standards
  • Experimental designWorkingChoose comparisons that identify credible effects
  • Lab automation and biosafetyWorkingIntegrate instruments and safe experiment execution

Other roles in drug discovery and molecular design

Hiring nowAI Drug Discovery ScientistAn AI Drug Discovery Scientist uses predictive models and experimental evidence to decide which targets and compounds are worth testing. They help…Hiring nowProtein Design ScientistA Protein Design Scientist designs protein sequences and structures that meet defined functional targets, then plans the experiments to prove they…EmergingAI Medicinal Chemistry SpecialistAn AI Medicinal Chemistry Specialist weighs model-generated compound suggestions against real chemistry judgement and decides what gets made and…

Related roles in other families

Hiring nowLaboratory Automation EngineerAutonomous laboratories and scientific agentsA Laboratory Automation Engineer connects instruments, control software and experiment records so that experiments run the same way every time. It…EmergingScientific Agent EngineerAutonomous laboratories and scientific agentsA Scientific Agent Engineer builds agents that carry out research tasks and show their evidence. It matters because scientists will only use an…EmergingClosed-Loop Experimentation ScientistAutonomous laboratories and scientific agentsA Closed-Loop Experimentation Scientist decides which experiment to run next, using models and the results already observed. They help a company…EmergingAutonomous Lab Safety EngineerAutonomous laboratories and scientific agentsAn Autonomous Lab Safety Engineer sets and tests the limits on what a model can ask a laboratory to do. Without them, an agent that plans…

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.

← Drug discovery and molecular designAll new job families

Start a search

Hiring a Molecular Generative Modelling 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.