EmergingAutonomous laboratories and scientific agents

Closed-Loop Experimentation Scientist

Also called Self-Driving Lab Scientist

A Closed-Loop Experimentation Scientist decides which experiment to run next, using models and the results already observed. They help a company reach confirmed scientific findings with fewer, better-chosen experiments.

What they do

The work is choosing experiments in sequence. They build or adapt models that estimate what is known and what is uncertain, then pick the next run to learn the most. They connect those choices to instruments through APIs and lab workflow engines, so runs happen with little manual handling. They set limits on what an automated system may attempt, especially on safety. They check results for instrument drift and odd data, update the models, and decide whether to continue, change course or stop. Every decision and calibration step is written down so scientists can review it later.

What a strong hire delivers

In the first months, a strong hire gets one real experimental campaign running end to end, with a clear question and a stated stopping rule. Decisions and calibration are recorded so others can audit them. The team can see how much each round taught them. Safety limits are agreed and built into the workflow. The first confirmed result is checked by hand, not just trusted from the model.

How you can tell they are good

Ask them to walk through a campaign they ran, from the first model to the final result. Good candidates explain why each experiment was chosen, what went wrong and how they knew. They can describe how they tested model uncertainty against reality. They are specific about safety limits and when a human stepped in. Be wary of vague claims about optimisation with no confirmed scientific outcome.

Why it is hard to fill

This work is emerging and often sits inside other titles, such as automation engineer, computational scientist or research scientist. Few people have done all of it. Most are strong in one area, such as Bayesian methods, lab robotics or a scientific domain, and thin in the others. Job titles rarely match the work, so searching by title misses good people. We look at what candidates have actually run.

Where to find them

They tend to come from laboratory automation teams, scientific software groups, robotics groups and experimental research labs. Look for titles such as automation scientist, computational chemist or biologist, research engineer and machine learning scientist in the physical sciences. Academic groups running automated platforms are a common source, as are start-ups building autonomous labs and R&D teams in materials, chemistry and biotechnology.

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 Closed-Loop Experimentation Scientist

  1. Describe a campaign where models chose the next experiment. What was the question, and what did you learn?

    A strong answer names the objective, the model, the number of rounds in general terms and the confirmed outcome. Listen for what the loop taught them. Worry if they only describe tooling or cannot separate model gains from real findings.

  2. How do you decide which experiment to run next when you are uncertain about the model itself?

    Good answers cover acquisition choices, balancing exploration and exploitation, and checking model assumptions. They mention cost and risk of each run. Worry if they treat one method as always right.

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

Job description you can post

We are building systems where models choose experiments and automated instruments run them. We need a scientist who can design the decision logic, keep it safe and show that it produces real scientific progress. You will work with bench scientists, software engineers and automation specialists.

What you will do

  • Design and run experimental campaigns where each run is chosen from earlier results
  • Build and test sequential models that estimate uncertainty and guide experiment selection
  • Connect decision logic to instruments through APIs and workflow engines
  • Define and enforce safety limits on automated experiments
  • Monitor data quality, calibration and instrument drift
  • Keep clear records of decisions and calibration for review
  • Confirm key findings with independent checks

What you will bring

  • Demonstrated work running experiments where results shaped later choices
  • Hands-on use of active learning or Bayesian experiment design
  • Experience with laboratory automation, scientific software or robotics
  • Solid knowledge of at least one scientific domain relevant to our work
  • Understanding of lab safety and biosafety practice
  • Ability to explain model decisions to non-specialists
  • Clear, careful record keeping

Nice to have

  • Experience orchestrating agents that plan or run experiments
  • Experience with lab workflow engines
  • Work on a self-driving laboratory

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

Skills that matter

  • Lab automation and biosafetyAdvancedIntegrate instruments and safe experiment execution
  • Agent orchestrationAdvancedCoordinate tool-using agent execution
  • Scientific domain expertiseWorkingApply disciplinary theory and experimental standards
  • Experimental designWorkingChoose comparisons that identify credible effects

Other roles in autonomous laboratories and scientific agents

Hiring nowLaboratory Automation EngineerA Laboratory Automation Engineer connects instruments, control software and experiment records so that experiments run the same way every time. It…EmergingScientific Agent EngineerA Scientific Agent Engineer builds agents that carry out research tasks and show their evidence. It matters because scientists will only use an…EmergingAutonomous Lab Safety EngineerAn 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…

Related roles in other families

Hiring nowAI Drug Discovery ScientistDrug discovery and molecular designAn AI Drug Discovery Scientist uses predictive models and experimental evidence to decide which targets and compounds are worth testing. They help…Hiring nowProtein Design ScientistDrug discovery and molecular designA Protein Design Scientist designs protein sequences and structures that meet defined functional targets, then plans the experiments to prove they…EmergingMolecular Generative Modelling ScientistDrug discovery and molecular designA molecular generative modelling scientist builds models that propose new, chemically valid compounds under clear constraints. They give a drug…EmergingAI Medicinal Chemistry SpecialistDrug discovery and molecular designAn AI Medicinal Chemistry Specialist weighs model-generated compound suggestions against real chemistry judgement and decides what gets made and…

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.

← Autonomous laboratories and scientific agentsAll new job families

Start a search

Hiring a Closed-Loop Experimentation 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.