2026 Future Talent Program - Data Science Co-op (proteomics & Genetics)

Merck Merck · Pharma · MA

This role focuses on curating, preprocessing, and integrating large-scale proteomics, genetics, and multi-omics datasets for biomarker and target discovery. It involves exploring and developing statistical and AI/ML approaches for these purposes, and building causal networks. The role is within a Research and Development division at Merck, specifically in the Precision Genetics group.

What you'd actually do

  1. Curate and preprocess biobank-scale proteomics and other omics datasets (e.g., UK Biobank) according to project needs.
  2. Integrate proteomics, genetics, and clinical data to perform association analyses and stratified analyses for target and biomarker discovery.
  3. Build and compare protein- and pathway-level causal networks across cohorts and disease states to interpret molecular relationships.
  4. Explore and develop statistical and AI/ML approaches leveraging multi-omics data for biomarker discovery and patient stratification.
  5. Collaborate with cross-functional teams (computational biology, statistical genetics, AI/ML, and therapeutic-area experts).

Skills

Required

  • R
  • Python
  • version control

Nice to have

  • large-scale omics datasets
  • statistical genetics methods
  • biobank or consortium datasets
  • secure research environments
  • scalable/parallel workflow design
  • network/graphical models
  • ML methods applied to genomics

What the JD emphasized

  • AI/ML approaches

Other signals

  • AI/ML approaches
  • multi-omics data
  • biomarker discovery
  • patient stratification