2026 AI/ML Biotherapeutics Development Intern

PhD

Posted on 11/13/2025

AbbVie

AbbVie

No salary listed

San Bruno, CA, USA

In Person

Job Description

AI/ML Biotherapeutics Development Internship Overview 

Envision spending your summer working with energetic colleagues and inspirational leaders, all while gaining world-class experience in one of the most dynamic organizations in the pharmaceutical industry. This is a reality for AbbVie Interns.  

The Quantitative, Translation & ADME Sciences (QTAS) team in South San Francisco supports the characterization, modeling the ADME (Absorption, Distribution, Metabolism, and Excretion) aspects of drug development research, part of which focuses on enhancing biologics property prediction through innovative AI/ML methods. This internship involves exploring explicit structural data integration into deep learning models for biologics sequence-to-property prediction, tapping into dynamic protein conformations through ensemble structures.  

Key responsibilities include: 

  • Evaluate and analyze structures of biologics. 

  • Explore and implement state-of-the-art techniques to improve AI/ML models. 

  • Collaborate with AI/ML and computational biology experts to refine modeling strategies and achieve predefined success metrics 

Qualifications

Minimum Qualifications  

  • Currently enrolled in university, pursuing a PhD in Computer Science, Computational Biology, Biophysics, or other related field. 

  • Must be enrolled in university for at least one semester following the internship.  

  • Demonstrated experience with deep learning concepts and experience with Python and PyTorch. 

  • Familiarity with protein language models. 

  • Familiarity with protein structure data (e.g., PDB files) and structural biology concepts.  

  • Excellent communication, problem-solving, and collaboration skills. 

Preferred Qualifications 

  • Expected graduation date between December 2026 – June 2027. 

  • Antibody-related knowledge.   

  • Experience with molecular dynamic simulations or other protein structural sampling techniques. 

  • Experience with Graph Neural Network (GNN) models.