Principal Data Scientist

Principal Data Scientist at Veracyte. Remote (US/Canada), San Diego, or South San Francisco.

Lead the research and creation of multimodal AI (MMAI) models and workflows integrating genomic, transcriptomic, imaging, and clinical oncology data. Reports to Senior Director of Computational Biology.

Key Responsibilities

• Lead MMAI model research collaborating on strategy, cohort selection, and data acquisition
• Design and train models integrating genomics, transcriptomics, whole-slide imaging, and clinical features for cancer prognosis and therapy selection
• Drive proof-of-concept projects from conception through validation and publication
• Build pipelines for ingesting and harmonizing diverse data modalities
• Collaborate with cross-functional teams ensuring biological interpretability and clinical applicability
• Present findings via abstracts, publications, and reports

Required Qualifications

• Ph.D. in bioinformatics, computational biology, genomics, biostatistics, computer science, or related field
• 8+ years relevant experience; at least 5 in biotech, diagnostics, or healthcare
• Expertise in multimodal data integration, machine learning, and NGS-based clinical diagnostics
• Proficiency in Python, R, and SQL
• Cloud computing experience (AWS preferred)
• Deep knowledge of genomics, transcriptomics, digital pathology, and clinical analysis
• Established peer-reviewed publication record

Preferred

• Experience with advanced ML architectures (transformers, attention mechanisms)
• HIPAA and GDPR regulatory knowledge
• Medical imaging and cytopathology background