Grad Intern - Computational Chemistry (summer 2027)

Amgen•Thousand Oaks, CA
•$35 - $41

About The Position

Amgen is seeking a summer 2027 graduate intern to join its Computational Chemistry team. Computational chemistry supports Amgen’s drug discovery work by helping accelerate the pipeline from target inception to drug development. The intern will develop and evaluate molecular property prediction models for predictive performance and interpretability, supporting the discovery of small-molecule therapeutics. The intern will investigate ways to make models accessible through conversational AI agents, apply interpretability methods to understand how molecular features influence predictions and explore structure–property relationships. The role includes literature review, collaboration with interdisciplinary teams, communication of project progress and findings, and documenting methods and analyses to support reproducible research. The internship requires full-time availability, continued enrollment at an accredited college or university after the program, and presence in the United States for the duration of the internship. Candidates must be authorized to work in the U.S. during the program. The U.S. base pay range is $35.34–$41.20 per hour.

Requirements

  • Must be 18 years or older.
  • Must have graduated with a bachelor’s degree from an accredited college or university.
  • Must be currently enrolled in an accredited Ph.D. program and have completed the first year before the internship starts.
  • Must be available to work a full-time schedule.
  • Must remain enrolled in an accredited college or university following the internship program.
  • Must be located in the United States for the duration of the internship.
  • Must be authorized to work in the United States for the duration of the program.

Nice To Haves

  • A degree in Computational Chemistry, Cheminformatics, Computational Biophysics, Data Science, or a similarly quantitative field.
  • Familiarity with machine learning models for molecular property prediction, including model development and evaluation of predictive performance.
  • Experience processing and analyzing molecular data using cheminformatics tools such as RDKit, and familiarity with model interpretability methods for exploring structure–property relationships.
  • Demonstrated programming and data analysis experience in Python, with familiarity with Unix-based systems and version control software such as Git.
  • High motivation and enthusiasm for science and problem solving.
  • Research contributions through peer-reviewed publications or presentations at scientific conferences.

Responsibilities

  • Develop and evaluate machine learning models for molecular property prediction.
  • Assess predictive performance using appropriate metrics.
  • Explore approaches to making models accessible through conversational AI agents.
  • Apply model interpretability methods to investigate how molecular features influence predictions and explore structure–property relationships.
  • Collaborate with interdisciplinary teams to support successful project execution and implementation.
  • Review and summarize project-related literature.
  • Communicate findings and progress effectively to team members.
  • Document methods and analyses clearly to support reproducible research.

Benefits

  • Competitive benefits.
  • Collaborative culture.
  • Opportunities to build a professional network.
  • Executive and social networking events.
  • Community volunteer projects.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service