Senior Machine Learning Scientist, BRAID (Clinical Sciences ML)

Roche • South San Francisco, CA

89d • Onsite

About The Position

A healthier future. It’s what drives us to innovate. To continuously advance science and ensure everyone has access to the healthcare they need today and for generations to come. Creating a world where we all have more time with the people we love. That’s what makes us Roche. 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 new Computational Sciences Center of Excellence (CoE) is a strategic, unified group whose goal is to harness the 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 Opportunity Genentech is seeking an exceptional Senior Machine Learning Scientist to join the BRAID (Biology Research | AI Development) team within our Computational Sciences organization. This role will focus on developing novel machine learning methods to transform clinical trial design and translational medicine, with a strong emphasis on foundation models for clinical genomics and real-world data. You will work at the intersection of machine learning, omics (DNA, RNA), and EHR data, advancing algorithms that integrate biological and clinical modalities to improve patient stratification, target selection, and treatment outcomes. The ideal candidate will possess in-depth expertise in modern machine learning approaches (e.g., transformer-based models, generative modeling, representation learning) and a track record of impactful research in clinical genomics or multimodal biomedical data analysis. A passion for interdisciplinary collaboration and a commitment to open scientific communication are essential.

Requirements

• Ph.D. in Computer Science, Machine Learning, Statistics, Mathematics, Physics, or a related field.
• Proven track record of developing and applying advanced ML models in a research or industry setting.
• Proficiency in scientific programming languages such as Python as well as MLOps workflows (e.g., familiar with code version control, high-performance compute infrastructures, and machine learning experiment monitoring workflows)
• Strong experience with ML frameworks such as PyTorch, JAX, or TensorFlow.
• Solid foundation in probabilistic modeling, deep learning, and representation learning.
• Excellent communication, collaboration, and problem-solving skills.
• Strong publication record in ML, bioinformatics, or computational biology venues (e.g., NeurIPS, ICML, ICLR, RECOMB, Bioinformatics).

Nice To Haves

• Prior experience developing foundation models for omics or EHR data, including pretraining or fine-tuning strategies.
• Deep knowledge of representation learning, generative modeling (e.g., VAEs, diffusion models, masked transformers), and multi-modal learning.
• Experience integrating biological priors (e.g., pathways, ontologies, knowledge graphs) into model design.
• Passion for advancing healthcare through innovation in ML and computational biology.

Responsibilities

• Design and implement novel machine learning algorithms tailored to the complexities of clinical trial data (e.g., sequence models for patient omics data).
• Collaborate with cross-functional teams including biologists, clinicians, data scientists, and other stakeholders to integrate machine learning solutions into clinical decision-making.
• Work closely with biologists, clinicians, and translational scientists to develop clinically meaningful AI tools that integrate molecular signatures, patient trajectories, and trial outcomes.
• Analyze large-scale datasets including whole transcriptome, whole exome, and real-world clinical data to derive insights into disease progression, treatment response, and patient stratification.
• Maintain awareness of current research trends in machine learning for biomedicine and contribute to scientific leadership in this space.
• Publish research in top-tier ML and computational biology conferences and journals.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: Ph.D. or professional degree
• Number of Employees: 5,001-10,000 employees