2026 Summer Intern - Regev Lab - Computational Biology / Sequence Modeling

Roche•South San Francisco, CA

1d•$50 - $50•Onsite

About The Position

Genentech, a biotechnology leader, is seeking an outstanding machine learning intern to contribute to research at the intersection of genomics and AI, in collaboration with the Regev Lab and the ReLU team led by Gokcen Eraslan within the Biology Research AI Development (BRAID) department. This internship will focus on developing and applying sequence-aware machine learning methods for single-cell regulatory genomics, with the goal of improving how the regulatory state is represented, interpreted, and connected to broader cellular programs (e.g., gene expression). The work will support efforts to build unified, biologically meaningful representations of cellular state that can enable downstream scientific discovery. This internship position is located in South San Francisco, on-site. Over the course of the internship, you will work closely with a cross-functional team of machine learning scientists and computational biologists, and will be mentored by researchers from the Regev Lab and the ReLU team at BRAID. This is an opportunity to contribute to cutting-edge methods development in single-cell biology, with an emphasis on approaches that are robust, reproducible, and interpretable. Program Highlights Intensive 12-weeks, full-time (40 hours per week) paid internship. Program start dates are in May/June 2026. A stipend, based on location, will be provided to help alleviate costs associated with the internship. Ownership of challenging and impactful business-critical projects. Work with some of the most talented people in the biotechnology industry.

Requirements

Must be pursuing a PhD (enrolled student).
Computational Biology, Computer Science, Biology, or related computational field.
Deep Learning & Python Proficiency: Strong experience with Python and deep learning frameworks (specifically PyTorch). Familiarity with implementing or fine-tuning Transformer architectures and an understanding of generative models is highly desirable.
Computational Biology & Single-Cell Analysis: Experience working with single-cell genomic data formats (e.g., AnnData, MuData). Understanding of chromatin accessibility (ATAC-seq) and gene expression (RNA-seq) data processing, particularly regarding genomic intervals and cis-regulatory elements.
Foundation Model Fluency: Ability to read, digest, and implement concepts from recent literature on genomic foundation models (e.g., Decima, Nona, Enformer, Evo2) to create semantic encodings.
Scientific Communication: Ability to synthesize complex multimodal analysis into clear visualizations and communicate findings regarding regulatory heterogeneity to cross-functional teams.

Nice To Haves

Excellent communication, collaboration, and interpersonal skills.
Complements our culture and the standards that guide our daily behavior & decisions: Integrity, Courage, and Passion.
Generative Modeling: Experience with diffusion models and/or flow matching methods.
Permutation-Invariant Architectures: Familiarity with Set Transformers (or related attention-based set models).
Multimodal Modeling: Experience integrating multiple data modalities (e.g., sequence + single-cell readouts; ATAC + RNA) in shared representation spaces.