Research Assistant, AI-Driven Data Pipelines

The Pennsylvania State University; University Park (TX); On-site; USD 18,000 - 26,000; Part time

Job summary

Penn State University Park seeks a part-time Research Assistant to support a Smeal faculty team led by Professor Aydin Alptekinoglu. You will build and maintain an automated pipeline to collect faculty publications and working papers and develop search tools over the repository.

The role is up to 15 hours per week during the academic semester, starting at $16.00 per hour. Candidates should have strong Python skills, API experience including Crossref or similar, familiarity with LLM APIs,

Qualifications

• Currently enrolled Penn State student.
• Strong Python skills, including writing maintainable scripts and working with APIs.
• Experience collecting and cleaning data programmatically (e.g., scraping, publisher APIs).
• Familiarity with LLM APIs and prompt design.
• Basic understanding of embeddings, vector search, and retrieval-augmented generation.
• Comfort with Git and basic software testing practices.
• Ability to work independently and document code clearly.

Responsibilities

• Build and maintain an automated pipeline that collects Smeal faculty publications and working papers.
• Develop and test search and discovery tools over the repository.
• Support development of synthesis and translation features for faculty, research centers, marketing, and development.
• Test the system with a small pilot collection, then scale to the full collection.

Skills

Python

APIs

Data collection

LLM APIs

Embeddings

Git

Documentation

Independent work

Education

Currently enrolled Penn State student

Tools

Streamlit

Flask

Crossref API

Semantic Scholar API

SSRN API

Job description

Penn State University Park seeks a part-time Research Assistant to support a Smeal faculty team led by Professor Aydin Alptekinoglu. You will build and maintain an automated pipeline to collect faculty publications and working papers and develop search tools over the repository.

The role is up to 15 hours per week during the academic semester, starting at $16.00 per hour. Candidates should have strong Python skills, API experience including Crossref or similar, familiarity with LLM APIs,