Biological Data Scientist

Job Summary

Owning the data that drives innovative biological reasoning models, the full-time Biological Data Scientist will construct and enhance training datasets, develop methods to expand data coverage, and design benchmarks to ensure models learn biologically meaningful capabilities, all while working remotely.

Key responsibilities

• Construct training datasets that capture molecular interactions from diverse biological sources
• Develop methods to create new training signals using biological and chemical reasoning
• Design benchmarks to measure the biological relevance of model capabilities

Required qualifications

• PhD in computational biology, biophysics, structural biology, chemistry, biochemistry, or related field with 2+ years of post-doctoral or industry experience
• Deep understanding of molecular interactions and protein structure at the molecular level
• Experience with large-scale biological datasets, including sourcing, cleaning, and analyzing data
• Strong programming skills in Python for building computational data processing pipelines
• Understanding of machine learning model requirements for training data quality and evaluation