Staff Data Scientist, Genomics

Biohub seeks a data science leader to shape how biological data powers frontier AI models. The position combines strategic vision-setting with hands-on technical work, focusing on data representation and tokenization for genomic and multi-modal biological datasets.

Key Responsibilities

• Design data representation and tokenization strategies for diverse biological data types
• Establish data standards and quality metrics for cross-dataset integration
• Combine heterogeneous data modalities into unified training frameworks
• Assess how representation choices impact model performance and biological signal capture
• Collaborate with ML engineers and AI researchers on dataset design
• Lead cross-functional initiatives spanning engineering, science, and product teams
• Identify new data acquisition and generation opportunities
• Mentor staff and establish data science rigor standards

Required Qualifications

• PhD in computational biology, bioinformatics, or related quantitative field
• 8+ years with large-scale biological datasets (genomics, transcriptomics, proteomics, multi-omics)
• Deep knowledge of measurement types: sequencing, imaging, proteomics
• Experience designing data representations for machine learning applications
• Strong Python and scientific computing skills
• Expertise in ML/statistical modeling and modern architectures
• Cross-disciplinary communication abilities

Benefits

• 401(k) matching
• Volunteer time off
• Family-forming benefits
• Relocation support