Senior AI Scientist: Drug Discovery & Informatics

Merck & Co.; South San Francisco (CA); On-site; USD 160,000 - 251,000; Full time

Job summary

Merck & Co. is seeking a highly motivated computational scientist to join our South San Francisco laboratories. The role focuses on building AI/ML algorithms and workflows to advance drug discovery, integrating predictive modeling with physics-based insights and experimental feedback within the DMTA cycle.

The candidate will collaborate with medicinal and computational chemistry teams, mentor scientists, and contribute to publications while deploying methods across computational environments.

Qualifications

• Two+ years of hands-on DL model development with PyTorch/JAX or similar.
• Broad competency in modern data science.
• Research applying DL to chemistry/biophysics problems.
• Experience with agentic AI frameworks.
• Track record of publications in peer-reviewed journals.
• Strong Python for scientific programming on Linux HPC.
• Excellent written and oral communication skills.

Responsibilities

• Develop novel AI/ML algorithms for representation, prediction, generation, reasoning, and decision-making.
• Evaluate AI/ML methods against computational/experimental benchmarks.
• Develop deep-learning approaches for molecular discovery combining ML and physics-based insight.
• Create agentic workflows integrating models, data, and literature.
• Collaborate with medicinal and computational chemistry teams on design and prioritization.
• Build reproducible workflows and deploy methods across computational environments.

Skills

Python

Deep learning

Data science

Linux HPC

Scientific communication

Education

Bachelor's / Master's / PhD in Engineering, CS, ML, Chemistry, Computational Chemistry, Biophysics, Applied Mathematics

Tools

PyTorch

JAX

RDKit

Job description

Merck & Co. is seeking a highly motivated computational scientist to join our South San Francisco laboratories. The role focuses on building AI/ML algorithms and workflows to advance drug discovery, integrating predictive modeling with physics-based insights and experimental feedback within the DMTA cycle.

The candidate will collaborate with medicinal and computational chemistry teams, mentor scientists, and contribute to publications while deploying methods across computational environments.