Hiring nowAI for physics, mathematics and astronomy

Astronomy AI Scientist

Also called Astroinformatics Scientist

An Astronomy AI Scientist analyses astronomical observations with calibrated statistical learning. They give a company catalogues and detection models whose claims hold up under scrutiny, which protects its scientific credibility.

What they do

They take raw or lightly processed observations and turn them into detections, classifications or catalogues. Much of the day goes on understanding the data: instrument quirks, selection effects, noise and missing coverage. They build deep learning and statistical models, then test them against simulations and known sources. They quantify uncertainty on every output. They check how many detections are false and what the model misses. They write code that others can rerun, and they explain results to astronomers and engineers who will question them. They also work with simulation codes and observatory data tools.

What a strong hire delivers

In the first months, a strong hire delivers a working analysis pipeline on real observations, with clear validation against simulated and known data. They produce a first catalogue or detection model with stated false discovery and completeness figures. They document assumptions so results can be reproduced by someone else. They also leave the team with a shared view of where the data can and cannot be trusted.

How you can tell they are good

Ask them to walk through a past detection or catalogue project from raw data to final claim. A strong person explains selection effects, how they injected simulated signals, and how they set thresholds. Ask how they know the uncertainties are calibrated. Listen for specifics about failure cases. Be wary of anyone who quotes accuracy alone or cannot say what their model misses.

Why it is hard to fill

The title varies. People call themselves astroinformatics scientists, data scientists, research scientists or postdocs in astrophysics. The skill sits between astrostatistics and modern machine learning, and few people are strong at both. Many astronomers lack production engineering habits. Many machine learning engineers lack the instinct for selection effects and calibration. Candidates are often settled in academic posts, so the move needs a clear scientific case.

Where to find them

Look in astrophysics and cosmology groups, observatory and survey data teams, and scientific computing centres. Typical titles include postdoctoral researcher, survey scientist, astroinformatics scientist and research software engineer. Others come from physics, applied mathematics or statistics with a record of analysing instrument data. Some work at space and Earth observation companies, or at AI companies building scientific models.

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 an Astronomy AI Scientist

  1. Describe a detection or catalogue you built. How did you decide what to claim and what to leave out?

    A strong answer names the data, the thresholds and the reasoning for them. It covers false discoveries, completeness and known blind spots. Worry if they only talk about headline accuracy or cannot explain why they excluded anything.

  2. How do you test a detection model when true labels are scarce?

    Look for injected simulated signals, comparison with known sources, held-out regions and cross-checks with independent data. They should note where simulations differ from reality. Worry if they rely on a single random split.

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

Job description you can post

We are building AI systems that turn astronomical observations into trustworthy scientific results. We need an Astronomy AI Scientist to develop detection models and catalogues, validate them carefully, and work closely with engineers and domain scientists so that our claims stand up to scrutiny.

What you will do

  • Build detection, classification and catalogue models for astronomical observations
  • Design validation using simulations, injected signals and known sources
  • Measure and report false discovery rate and completeness
  • Quantify and calibrate uncertainty on model outputs
  • Investigate data quality, instrument effects and selection biases
  • Write reproducible, documented analysis code
  • Present results and limits to scientists and engineers

What you will bring

  • Demonstrated work analysing real astronomical or similar instrument data
  • Hands-on experience with deep learning for scientific data
  • Strong grounding in astrostatistics and uncertainty quantification
  • Evidence of validating models without abundant labels
  • Confident scientific computing skills in a team codebase
  • Clear written explanation of methods and limitations

Nice to have

  • Experience with simulation codes
  • Familiarity with formal verification or theorem provers
  • Published or public catalogues, code or analyses

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
  • Formal verificationAdvancedProve stated properties under explicit assumptions
  • Deep learningWorkingBuild and diagnose trainable neural models
  • Uncertainty quantificationWorkingEstimate confidence, calibration and model uncertainty

Other roles in aI for physics, mathematics and astronomy

Hiring nowPhysics-Informed ML ScientistA Physics-Informed ML Scientist builds learned models that respect physical laws, so a company can run fast, trustworthy approximations of costly…EmergingAI Mathematical Discovery ResearcherAn AI Mathematical Discovery Researcher uses learning systems and formal tools to propose conjectures and algorithms, then gets them independently…EmergingQuantum Machine Learning ResearcherA Quantum Machine Learning Researcher tests whether quantum methods can beat classical ones for learning problems under realistic limits. They save…

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.

← AI for physics, mathematics and astronomyAll new job families

Start a search

Hiring an Astronomy AI 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.