Senior Scientist, Computational Biology (Multimodal Data Integration)

Roche•South San Francisco, CA

23h•$130,800 - $242,800•Hybrid

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. Seamless data sharing and access to models across gRED and pRED are essential to maximising these opportunities. The 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 delivering more innovative and transformative medicines for patients worldwide. The sub-department of Oncology in Computational Biology and Medicine at Genentech is seeking a visionary and highly motivated Senior Scientist to join a newly forming team focused on Multimodal Data Integration. This role will focus on modeling high-dimensional data at the critical interface of disease biology and translational medicine. The successful candidate will be responsible for the vertical integration of diverse, disease-specific large datasets. In this role, you will work alongside experts in disease biology and drug development to address the missing link: integration across pre-clinical and clinical modalities to associate biological mechanisms with clinical outcomes. You will develop computational frameworks and advanced statistical models in partnership with other computational biologists to creatively address complex scientific questions from Research and Translational Medicine and to deliver actionable biological insights and therapeutic strategies.

Requirements

Ph.D. in Computational Biology, Systems Biology, Bioinformatics, or a related field with 0-2 years of significant postdoctoral or industry experience.
Proven track record in integrating data from multiple modalities (e.g., NGS, single-cell, proteomics, perturbational and clinical data) using advanced statistical modeling or systems biology.
Deep understanding of recent ML methods with a specific emphasis on model interpretability.
Expert-level fluency in R and Python.
Experience building scalable computational workflows for large-scale data integration is required.
Familiarity with AI-supported and agentic coding tools.
Strong foundation in cancer biology and oncogenic signaling.
Proficiency in communicating intricate biological principles is essential for facilitating productive collaborations and strategic alignment with experimental research leadership.
Ability to navigate ambiguity and partner with stakeholders to turn creative research ideas into impactful, innovative computational strategies.
Excellent skills in data visualization and the ability to present complex multimodal findings to diverse audiences (from ML scientists to clinical physicians).

Responsibilities

Lead the integration of multimodal datasets - including high-throughput transcriptomics, epigenomics, drug-response, and clinical data (e.g., ctDNA, imaging) - to enable multi-state modeling and patient subtyping.
Develop methods to associate pre-clinical model profiles (cell lines, organoids) with clinical segments to validate biomarkers and therapeutic targets.
Design and deploy computational workflows and frameworks leveraging statistical, computational biology and advanced machine learning methods to enable insight generation from high-dimensional profiling techniques.
Focus on "interpretable AI" - developing models that go beyond prediction to explain the underlying biology and mechanisms of action/resistance.
Co-create and lead technical roadmaps for complex experimental questions, acting as a creative bridge between experimental oncology and machine learning groups.
Provide the vision to transition from simple data processing to sophisticated biomarker development and mechanism-driven discovery.