Hybrid Single-Cell Genomics AI/ML Intern

Merck; Cambridge (MA); Hybrid; USD 40,000 - 111,000; Full time

Job summary

Merck is seeking an AI/ML Data Science intern in Cambridge, MA for a 10-12 week full-time program starting May or June 2027. The role focuses on developing statistical methods and pipelines to analyze perturb-seq datasets and to interpret in silico perturbation predictions from single-cell foundation models.

You will collaborate with a multi-disciplinary team, deliver robust Python-based software, and contribute to advancing biological data science projects within a hybrid work environment.

Qualifications

• Must be currently enrolled in a PhD degree in Computer Science, Statistics, Bioinformatics, Computational Biology, or related technical field.
• Must be available to work full-time for 10-12 weeks beginning in May or June of 2027.
• Demonstrated experience with single-cell omics data (e.g., scRNA-seq, perturb-seq).
• Excellent software design and development skills and strong proficiency in Python.
• Excellent communication skills and ability to work collaboratively in a multi-disciplinary team.

Responsibilities

• Develop statistical and computational methods/pipelines to utilize, analyze, interpret, and validate perturb-seq datasets.
• Develop approaches to assess, interpret, and validate in silico perturbation predictions from single-cell foundation models.

Skills

Python proficiency

single-cell omics data experience

communication and collaboration

software design and development

Education

PhD in Computer Science, Statistics, Bioinformatics, Computational Biology, or related field

Tools

PyTorch

Job description

Merck is seeking an AI/ML Data Science intern in Cambridge, MA for a 10-12 week full-time program starting May or June 2027. The role focuses on developing statistical methods and pipelines to analyze perturb-seq datasets and to interpret in silico perturbation predictions from single-cell foundation models.

You will collaborate with a multi-disciplinary team, deliver robust Python-based software, and contribute to advancing biological data science projects within a hybrid work environment.