2026 Summer Intern - Biology Research | AI Development

Roche•South San Francisco, CA

15d•$50•Onsite

About The Position

BRAID is a department within Genentech dedicated to advancing biological and clinical sciences through artificial intelligence. Our core focus is on developing foundation models—general-purpose AI models trained on large-scale biological datasets—which we fine-tune for specialized applications. Our research spans multiple areas, with key focuses including: High-throughput perturbative screening for target identification and drug discovery, utilizing technologies such as cell painting, Perturb-seq, and optical pooled screens. Regulatory element design for gene and cell therapy applications. Integration of multi-modal biological data to improve target assessment. Inference of cellular communication using spatial transcriptomics and proteomics. Virtual screening of small molecules for phenotypic drug discovery. Foundational machine learning, focusing on fine-tuning foundation models, generative modeling, causal inference, explainability, and uncertainty quantification. This internship position is located in South San Francisco, on-site. The Opportunity Large cohort single cell RNA-seq studies enable the study of disease across contexts at ultra-high resolution. As such atlas-scale datasets are becoming increasingly common, the need for scalable and interpretable computational methods for analyzing and gleaning insights regarding the underlying mechanisms of disease from such datasets is becoming increasingly high. Tensor factorization (TF) methods are promising approaches for studying structured systems biology datasets, and thus for modeling atlas-scale cohort studies. However, existing TF methods are not yet optimized and specifically designed for the analysis of atlas level single cell datasets. Furthermore, current applications of TF to the study of single cell datasets are purely data-driven, and are not yet able to leverage a priori biologically relevant knowledge, potentially limiting their interpretability and hampering their utility. The Li Lab [https://lilab-bcb.github.io/] is looking for an exceptional intern candidate to work on developing and applying a novel TF formulation that addresses the described computational challenges. The candidate will have opportunities to learn and implement state-of-the-art tensor decomposition algorithms and apply them to internally generated and public single cell atlas datasets. The proposed position will serve as an excellent opportunity for the candidate to not only hone their method development skills, but also to deepen their biological knowledge through the application of their newly developed tool to generate impactful insights from high-value datasets. Program Highlights Intensive 12-weeks, full-time (40 hours per week) paid internship Program start dates are May 18th or June 1st (Summer) 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, and learn from some of the most talented people in the biotechnology industry.

Requirements

Must be pursuing a PhD (enrolled student).
Computer Sciences / Computational Biology / Bioinformatics or Related Field
Strong background in computer science, statistics or mathematics
Proficient in Python programming language and its data science environment (e.g. Numpy, Scipy, Pandas, Scikit-learn)
Experience in single-cell genomics data analysis

Nice To Haves

Experience in dimensionality reduction and/or tensor decomposition methods such as non-negative matrix factorization or PARAFAC is a plus
Experience using relevant tools such as JAX and TensorLy is a plus
Experience applying computational tools to generate biological insights is a plus
Excellent communication, collaboration, and interpersonal skills
Complements our culture and the standards that guide our daily behavior & decisions: Integrity, Courage, and Passion