Description:

Stop by to learn about our paid Summer position in AI/ML in drug discovery.
Meet with the team and drop off your resume.

AbbVie is a global, research-based biopharmaceutical company formed in 2013. Our mission is to discover and deliver innovative medicines that solve serious health issues today and address the medical challenges of tomorrow. Our ~50,000 employees are scientists, researchers, communicators, manufacturing specialists and regulatory experts located around the globe. We strive to have a remarkable impact on people's lives across several key therapeutic areas: immunology, oncology, neuroscience, eye care, virology, women's health and gastroenterology, in addition to products and services across its Allergan Aesthetics portfolio. For more information about AbbVie, please visit us at www.abbvie.com. Follow @abbvie on Twitter, Facebook, Instagram, YouTube and LinkedIn.

Information Research Academic Partnerships embeds students within AbbVie businesses to collaborate on projects that help advance our science. During the regular fall and spring semesters, this program is designed for students to work 12-15 hours/week in parallel with their school schedule. During the summer, students are expected to work 35-40 hours/week.

The Global Research Informatics & Platform Solutions (GRIPS) Research AI team is dedicated to advancing machine learning solutions in the realm of early drug discovery for both small and large molecules. We work closely with R&D computational drug discovery teams to develop cutting-edge projects that include ML-based target assessment, molecular property prediction and de novo drug design. Our contributions support biologists and medicinal chemists during key stages such as target identification, hit generation, and lead generation. We are part of Information Research (IR), a larger organization that brings together computational and software-oriented professionals to create specialized software and data solutions for R&D.

The team is looking for three students to work on separate projects. Please see an overview of the responsibilities of each below:

v  LLM inference optimization for molecule generation

Ø  Engage in pioneering research and development initiatives focused on the application of large language models (LLMs) in drug discovery scenarios.

Ø  Develop advanced LLMs and associated applications, covering aspects such as model deployment, backend engineering, and tasks related to the evaluation, training, and fine-tuning of models.

Ø  Solve core ML and engineering challenges including the design, implementation, and scaling of our data, training, and deployment pipeline.

Ø  Work in close collaboration with cross-functional teams across IR and R&D departments to devise solutions to intricate problems in drug discovery. This collaborative effort will bridge computational insights with experimental needs.

v  Build an AI agent for de novo drug design

Ø  Engage in pioneering research and development initiatives focused on the application of large language models (LLMs) in drug discovery scenarios.

Ø  Design, build, and repeatedly refine an autonomous agentic framework to tackle complex drug discovery workflows. This includes fine-tuning the agent to efficiently manage tasks inherent to the drug discovery process.

Ø  Integrate innovative drug discovery applications and software into the agentic framework, enhancing its utility and versatility.

Ø  Develop advanced LLMs and associated applications, covering aspects such as model deployment, backend engineering, and tasks related to the evaluation, training, and fine-tuning of models. Collaborate closely with other engineers to ensure the solutions are scalable and reliable.

Ø  Work in close collaboration with cross-functional teams across IR and R&D departments to devise solutions to intricate problems in drug discovery. This collaborative effort will bridge computational insights with experimental needs.

v  Uncertainty Quantification and Explainable AI of predictive ML models for molecular property prediction (this role continues through December 2025)

Ø  Develop a tool that assesses the optimal uncertainty quantification (UQ) method for various machine learning models using existing benchmark frameworks (UNIQUE).

Ø  Suggest ways to quickly implement these optimal UQ methods in production for existing machine learning models.

Ø  Propose methods to explain the outputs of existing machine learning models, creating adaptable and reusable approaches applicable across different models.

Ø  Collaborate closely with cross-functional teams across IR and R&D departments. This collaboration aims to devise solutions to complex challenges in drug discovery, effectively bridging computational insights with experimental needs.

This position will begin in May 2025 and continue through August 2025.

For required qualifications, please visit McCormickConnect.