Member of the Technical Staff, Biological Data at Output

📋 Description

• Own data used by models; assess data scope and gaps.
• Build training datasets of proteins/molecules from diverse sources.
• Expand data beyond public databases using biological/chemical reasoning.
• Design benchmarks for biologically meaningful model capabilities.
• Plan data strategies with researchers; prioritize signals across modalities.
• Integrate diverse data across scales to create coherent training data.

🎯 Requirements

• PhD in computational biology/biophysics/chemistry or related; 2+ years postdoc/industry.
• Deep understanding of molecular interactions, protein structure, data.
• Experience with large-scale biological/molecular datasets: sourcing, cleaning, integrating, analyzing.
• Strong Python programming; building scalable data processing pipelines.
• Understand ML data needs: coverage, quality, balance, evaluation.
• Data construction as a research problem; think about signal and gaps.

🎁 Benefits

• We encourage new ideas, creativity and contrarian thinking.
• Healthy feedback-focused environment to help you grow and receive input.
• You own your day-to-day management; hit milestones.
• Competitive salary and equity in a growing startup.
• Excellent medical, dental, and vision coverage.