2026 Summer Intern - Computational Sciences CoE - Computational Biology and Medicine

Roche•South San Francisco, CA

1d•$50•Onsite

About The Position

Advances in AI, data, and computational sciences are transforming drug discovery and development. Roche’s Research and Early Development organisations at Genentech (gRED) and Pharma (pRED) have demonstrated how these technologies accelerate R&D, leveraging data and novel computational models to drive impact. The new Computational Sciences Center of Excellence (CoE) is a strategic, unified group whose goal is to harness this transformative power of data and Artificial Intelligence (AI) to assist our scientists in both pRED and gRED to deliver more innovative and transformative medicines for patients worldwide. The Synthetic Immunity team within the CS-CoE Computational Biology and Medicine department is seeking a talented and highly motivated Summer Intern with a strong computational and analytical background in computational biology, deep experience with single-cell RNA-seq data, and Large Language Models (LLMs). This internship position is located in South San Francisco, on-site. The Opportunity Lead the development of a Transformer-based Language Model using the Cell to Sentence or similar frameworks to learn robust cell representations. Aggregate, clean, and integrate large single-cell RNA-seq datasets. Apply the trained LLM to fine-tune tasks, such as predicting phenotype shifts. Work closely with established computational scientists to drive computational research in the pre-clinical. Program Highlights Intensive 12-week, full-time (40 hours per week) paid internship. The program start date is June or May. 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)
Required majors: Computational Biology, Bioinformatics, Computer Sciences, or a related field.
Proficiency in Python and PyTorch.
Track record of developing or applying deep generative models and machine learning techniques to capture robust cell representations and perform dataset integration.
Conceptual understanding of transformer architecture and practical experience with self-supervised objectives for sequence data.
Expert proficiency with the single-cell ecosystem, including scanpy and working with large-scale AnnData objects.
Track record of working with single-cell RNA-sequencing data and application of machine learning techniques to cell representations. This includes, but is not limited to, knowledge of single-cell data processing methods and dataset integration, and machine learning methods to capture cell representations.
Experience working with Git for version control and utilizing High-Performance Computing (HPC) resources.

Nice To Haves

Knowledge of T cell biology and experience working with TCR sequencing data is a plus.
Excellent communication, collaboration, and interpersonal skills.
Detail-oriented, goal-driven, and dedicated to delivering high-quality results.
Complements our culture and the standards that guide our daily behavior & decisions: Integrity, Courage, and Passion.

Responsibilities

Lead the development of a Transformer-based Language Model using the Cell to Sentence or similar frameworks to learn robust cell representations.
Aggregate, clean, and integrate large single-cell RNA-seq datasets.
Apply the trained LLM to fine-tune tasks, such as predicting phenotype shifts.
Work closely with established computational scientists to drive computational research in the pre-clinical.