Senior Data Scientist – Neuroscience Spatial Multi-omics

Merck Merck · Pharma · MA

Senior Data Scientist at Merck focused on analyzing spatial and single-nucleus multi-omics data for neurodegenerative diseases, leveraging AI/ML for target pathway biology, causal modeling, and biomarker discovery. The role involves building analytic workflows, integrating diverse omics data, and collaborating with cross-functional teams to shape translational strategies.

What you'd actually do

  1. Build and deploy analytic workflows leveraging state-of-art computational methods to analyze spatial multi-omics datasets, with a specific focus on target MOA evaluation and biomarker discovery in neurodegenerative diseases.
  2. Formulate and drive integration of spatial and single-nucleus multi-omics data to build unified predictive framework capturing the interactions among different CNS cell types (e.g., neurons and microglia).
  3. Lead data analytic projects to evaluate therapeutic hypothesis, drive precision biomarker discovery, inform translational strategies, and enable data-driven decision-making of multiple neuroscience drug discovery programs.
  4. Collaborate with internal AI/ML teams to develop and incorporate new methodologies into existing frameworks to enhance data analysis capabilities.
  5. Work with experimental biologists, functional area experts, and clinical scientists to support drug discovery and development programs at various stages.

Skills

Required

  • PhD in Data Science, Computational Biology, Computer Science, Genetics/Genomics, Biophysics, Bioinformatics, Statistics, Neuroscience, Neurology, or a related STEM discipline and 0+ years of experience, or an MS and 5+ years of experience.
  • Deep understanding of computational methodologies for single-cell and spatial transcriptomics analysis and extensive experience in their applications, preferably in neurological disorders.
  • Extensive experience in analyzing spatial transcriptomics data with single/sub-cell resolution (e.g., CosMx, Visium HD).
  • Demonstrated expertise in leveraging advanced AI/ML models (e.g., transformers, foundation models) and in silico perturbation simulation.
  • Ability to critically evaluate and apply novel data analysis methods in translational applications.
  • Proficient in one or more programming languages (e.g., Python, R), HPC environments and/or cloud-based platforms, as well as version control systems (e.g., Github).
  • Strong problem-solving skills, self-motivated, attention to detail, and ability to handle multiple projects.
  • Extensive experience to conduct research in a collaborative environment and excellent ability to communicate scientific questions, methodologies, findings and insights.
  • Proven track record (e.g., peer-reviewed publications) of extracting actionable insights from analysis of spatial/single-cell omics data.

Nice to have

  • Outstanding scientific caliber with strong capabilities to identify key analytic questions and formulate rigorous data analytic plans to address critical scientific needs of drug discovery programs.
  • Good understanding of neurobiology, particularly neurodegenerative diseases.
  • Familiarity with large public single-nucleus multi-omics datasets from neurodegenerative disease patient cohorts (e.g, ROSMAP, SEA-AD).
  • Additional 2+ years of multi-omics data analytics experience post final degree is preferred.

What the JD emphasized

  • track record of developing and applying cutting-edge AI/ML methodologies
  • Proven track record (e.g., peer-reviewed publications) of extracting actionable insights from analysis of spatial/single-cell omics data

Other signals

  • AI/ML methodologies
  • spatial and single-nucleus multi-omics data
  • causal modeling
  • predictive framework