Skip to main content Skip to navigation

The university has paused implementation of the COVID-19 vaccine mandate due to an injunction issued by a federal court. UW–Madison employees remain subject to the COVID-19 Workplace Safety Policy. Please visit covidresponse.wisc.edu for more information.

University of Wisconsin–Madison

Student Jobs

University of Wisconsin–Madison

Filter

Mining GALAH DR4 for Planet-Eating Stars - OSPO Fall Internship Program

Apply now(opens in a new window) Job No: 511850
Division/Organization: Office of the Vice Chancellor for Research
Department: Data Science Institute
Job Type: UW Student Jobs
Remote Eligbility: Partially Remote
Location: Morgridge Hall
Salary/Wage Range or Lump Sum: $15.00-17.00
Job Categories: Interpersonal Communication, Critical Thinking/Problem Solving, Digital Technology, Teamwork/Collaboration, Professionalism/Work Ethic, Information Technology and Computers, Data Analysis

Department Overview:

The Open Source Program Office (OSPO) is looking to connect interns with meaningful open-source projects as part of a new cohort of the internship program in collaboration with Madison College. During the internship, students will join a mentored open source project, participate in an initial training session, and weekly check-ins with the Open Source Program Office, and learn crucial skills related to managing open source software projects and growing software user communities.

Anticipated Start Date:

9/14/2026

Anticipated End Date (If Applicable):

11/20/2026

Remote Work Eligibility Detail:

Partially Remote

 

Anticipated Hours Per Week:

Minimum: 10 Maximum: 15

Schedule:

Internship work schedules will be established in collaboration with the project mentors, with a general expected commitment of 10-15 hours/week. In addition to the work schedule established with the project lead, interns will participate in a weekly group session with the OSPO for check-ins, trainings, and guest speakers.

Salary/Wage Range/Lump Sum:

Minimum: $15.00 Maximum: $17.00

Number of Positions:

1

Qualifications:

UW-Madison and Madison College undergraduate and graduate students with applicable backgrounds in any field are eligible to apply. Students must be enrolled in a degree program during the calendar year with at least one semester remaining after the internship’s conclusion.

Application materials should include:
- A one-page cover letter that highlights your qualifications based on skills identified in the project listing and your interest in open source broadly.
- A resume that includes your name, school email address, phone number, field(s) of study (major, minor, degree, certificate), relevant coursework, extracurricular activities, expected graduation date, relevant sample work (ex: GitHub link, personal website, etc.) and any relevant work or research experience.
-The names and contact information of three references.

Submit a resume, cover letter, and three references as part of your application.

Knowledge, Skills & Abilities:

The intern must be fluent in Python programming and familiar with machine learning tools and frameworks such as scikit-learn, PyTorch, or TensorFlow, as all development will be conducted in Python. Essential skills include experience with data analysis and visualization libraries (numpy, pandas, matplotlib), understanding of ML concepts including training/validation/testing, overfitting, regularization, and cross-validation, and comfort with Git/GitHub for version control. Strong problem-solving abilities, independent work skills, and excellent written and verbal communication are required, along with genuine interest in astronomy and willingness to learn about stellar physics.

The ideal candidate is a sophomore or junior undergraduate student (preferred to enable multi-semester engagement) who is interested in continuing work over multiple semesters and pursuing first-author publication. No prior astronomy research experience is required.

Position Summary/Job Duties:

When a star engulfs a planet, it can pick up two chemical fingerprints: an excess of refractory (rock-forming) elements, which shows up as a rising trend of abundance with condensation temperature, and extra lithium, which ordinary main-sequence stars slowly destroy. We do not have a list of which stars are engulfment cases, so this project frames discovery as anomaly detection: first find the chemically unusual stars, then test whether their peculiarity really points to planetary engulfment.

The intern will train a neural density model (a normalizing flow or autoencoder) on the roughly thirty elemental abundances plus lithium in the GALAH DR4 dataset, which contains nearly one million stars. By conditioning on temperature, gravity, and metallicity, the model learns what "chemically normal" looks like for each kind of star, flagging the stars it fits poorly as outliers. Those outliers are ranked along the two physically meaningful axes, the condensation-temperature slope and the lithium excess, to pull engulfment-like candidates out from other kinds of oddballs such as binaries or evolved-star pollution.

The scientific crux is separating real engulfment from look-alikes, because lithium also tracks age and a refractory excess can simply reflect a star's birth gas. To handle this, each candidate will be compared against control stars that match it in temperature, gravity, metallicity, and age, ideally stars born together with it in a wide binary or cluster. If the candidate stands out from these near-twins specifically in lithium and refractory slope, engulfment becomes the most likely explanation.

The intern will release two products: the anomaly-detection framework as an open-source Python package, and a public, ranked catalog of engulfment candidates. A central goal is for the intern to lead a first-author publication on the work. The project suits a computer science student interested in unsupervised and generative deep learning, and no astronomy background is required, since the needed concepts will be taught along the way.

Physical Demands:

Interns are expected to be able to sit for extended periods. Specific physical demands will be discussed with mentors during the interview process.

Institutional Statements:

Equal Employment Opportunity Statement:

UW-Madison is an Equal Employment, Equal Access Employer committed to increasing the diversity of our workforce.

Institutional Statement on Diversity:

Diversity is a source of strength, creativity, and innovation for UW-Madison. We value the contributions of each person and respect the profound ways their identity, culture, background, experience, status, abilities, and opinion enrich the university community. We commit ourselves to the pursuit of excellence in teaching, research, outreach, and diversity as inextricably linked goals.

The University of Wisconsin-Madison fulfills its public mission by creating a welcoming and inclusive community for people from every background-people who as students, faculty, and staff serve Wisconsin and the world.

For more information on diversity and inclusion on campus, please visit: diversity.wisc.edu

Accommodation Statement:

If you need to request an accommodation because of a disability, you can find information about how to make a request at the following website:https://employeedisabilities.wisc.edu/disability-accommodation-information-for-applicants/

 
 

Advertised: Central Daylight Time
Applications close: Central Daylight Time

Back to search results Apply now Refer a friend