2027 Summer Intern - Translational Safety (Computational Toxicology)

Roche•South San Francisco, CA
•$41 - $52•Onsite

About The Position

The Computational Toxicology group within Genentech’s Translational Safety organization is seeking a motivated summer intern to develop and apply computational approaches to biological questions in target safety research. The project will use single-cell transcriptomic and multi-omics data, alongside AI/ML methods, to investigate biological systems relevant to preclinical safety assessment. The specific research focus may be refined based on the intern’s interests and project needs. The intern will work with an interdisciplinary team to develop reproducible computational workflows for integrating and analyzing single-cell transcriptomic and multi-omics datasets; characterize in vitro models and assess their biological relevance through quantitative analyses and comparisons with reference datasets; explore and benchmark AI/ML methods, including foundation models, for high-dimensional biological data; and collaborate with computational and experimental scientists to interpret findings and contribute to reusable analysis tools, including LLM-based or agentic workflows where appropriate. This is an intensive, paid, 12-week, full-time internship of 40 hours per week, located on-site in South San Francisco. Program start dates are in May or June. A location-based stipend is provided to help alleviate internship costs. Relocation benefits are not available.

Requirements

  • Must be pursuing a master's degree as an enrolled student, have attained a master's degree, or be pursuing a PhD as an enrolled student.
  • Required majors include Bioinformatics, Computational Biology, Bioengineering, Computer Science, Data Science, Statistics, Machine Learning & AI, or related fields.
  • Experience with Python or R for scientific data analysis and computational workflows.
  • Familiarity with biological datasets, such as gene expression or other omics data, and associated sample and experimental metadata.
  • Ability to explore, quality-check, analyze, and interpret complex biological datasets.
  • Ability to document methods and maintain reproducible analyses using version control tools.
  • Strong problem-solving, communication, and teamwork skills.

Nice To Haves

  • Familiarity with single-cell RNA-seq concepts and analysis tools such as Scanpy/AnnData, Seurat, or scVI.
  • Experience with differential expression, pathway analysis, or comparative transcriptomics across biological models.
  • Interest in machine learning, representation learning, or foundation-model applications to biological data analysis.
  • Familiarity with LLM-based tools and agentic workflows for scientific research.
  • Complements the company’s culture and standards of Integrity, Courage, and Passion.

Responsibilities

  • Develop reproducible computational workflows to integrate and analyze single-cell transcriptomic and multi-omics datasets.
  • Characterize in vitro models and assess their biological relevance through quantitative analyses and comparisons with reference datasets.
  • Explore and benchmark AI/ML methods, including foundation models, for analyzing high-dimensional biological data.
  • Collaborate with computational and experimental scientists to interpret findings.
  • Contribute to reusable analysis tools, including LLM-based or agentic workflows where appropriate.

Benefits

  • Paid internship.
  • Location-based stipend to help alleviate costs associated with the internship.
  • Paid holiday time off benefits.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service