Intelligent Document Processing

Application deadline: January 1, 2027, 11:59 PM Eastern Time Zone.

About the role

The National Energy Technology Laboratory's (NETL) Professional Internship Program is designed to introduce undergraduate students and recent Bachelor's graduates to energy research challenges, and enable graduate students and recent Master's graduates to further build on their studies and experience as they join the scientific community. Participants interact daily with assigned mentors, become integral members of project teams, and contribute to pressing scientific questions using state-of-the-art equipment.

This posting seeks a recent Bachelor's graduate, recent Master's graduate, or student researcher to engage in projects with the Research Innovation Center (RIC) at NETL in the area of Intelligent Document Processing under the mentorship of Greg Lackey. The project will be hosted at the NETL Pittsburgh, PA campus.

The Subsurface Simulation Group is seeking a participant to collaborate in interdisciplinary research within the Oil & Gas Center of Excellence. The research focuses on intelligent document processing (IDP) for subsurface applications, specifically developing open-source IDP software to extract valuable data from scanned records describing energy infrastructure such as wells and reservoirs.

Responsibilities

• Test and validate open-source methods for extracting structured data from scanned records.
• Integrate open-source large language models into IDP research software.
• Improve the user interface and user experience of IDP research software.
• Conduct research for a full-stack production system including Python/FastAPI, MongoDB, and a TypeScript/React client.
• Apply AI and machine learning to real-world energy industry data challenges.
• Collaborate and communicate with an interdisciplinary team to extend an existing codebase with active users.
• Submit pre-appointment and post-appointment surveys, as well as a reflection on the appointment experience.
• Contribute to manuscripts, journal articles, conference presentations, posters, patents, and other publications as part of the appointment.

Qualifications

• Pursuing or recently completed a graduate degree in computer science, information science, or another relevant STEM field.
• Previous experience with web development, machine learning, databases, and cloud platforms using Python and JavaScript.
• Experience with version control using Git.
• One of the following academic statuses:
  • Undergraduate student in good standing at a regionally accredited college/university.
  • Recent Bachelor's degree graduate (degree received within the last 60 months).
  • Graduate student in good standing at a regionally accredited college/university.
  • Recent Master’s degree graduate (degree received within the last 60 months).
• Overall GPA of 2.5/4.0 or higher.
• At least 18 years of age at the time of application.
• Confirmation of coverage under a health insurance plan prior to the beginning of the internship.
• U.S. Citizen or Lawful Permanent Resident (LPR).

Skills

• Computer Science
• Information Science
• Web Development (Python, JavaScript, TypeScript, React, FastAPI)
• Machine Learning and AI
• Databases (MongoDB)
• Version Control (Git)
• Cloud Platforms
• Data Extraction and Processing
• Full-Stack Development
• Collaboration and Communication in Interdisciplinary Teams

Benefits

• Participants receive a biweekly stipend (taxable as an educational benefit):
  • $775.50 per week for undergraduate students.
  • $1206 per week for recent Bachelor's graduates.
  • $1475.50 per week for graduate students and recent Master's graduates.
• Opportunity to contribute to publications, presentations, patents, and other scholarly outputs.
• Networking with world-class scientists and researchers.
• Hands-on experience with state-of-the-art equipment and real-world energy research challenges.